eugenelim
- 173 skills
- 0 followers
- 28 repo stars
- 5 days ago last updated
- ▌ UX Writing 2 · eugenelim bundleUse when shaping the actual words a user reads in a product's UI — characterizing the UI copy voice (how the brand register applies to UI states), writing recurring UI-state microcopy (error, empty, button, label), or reviewing copy before it ships. Triggers on "what should this error say", "write the empty-state copy", "name this button", "characterize our product's UI copy voice", "make this microcopy blame-free", "review this copy". Characterizes voice along a few axes, writes each UI state from a blame-free + actionable formula, and runs a content checklist. When a per-screen state matrix from `user-flow` is present, writes copy per screen × state keyed to the matrix; when absent, behaves as today. Do NOT use to frame the intent behind the feature (use `intent frame`), to make visual or layout design decisions, to write documentation prose (use `author-product-docs` if installed), or to establish the brand-level copy register (use `content-design`'s brand-level register mode).
- ▌ Jira Epic Outcome View · eugenelim bundleUse this skill when someone wants to see what a Jira project's Epics have delivered beside what that work was meant to change -- "show me our Epics and their outcomes for PROJ", "which Epics are moving and what are they for", "what did we ship this quarter and why". Groups a project's work by Epic, counts delivery from the flow-metrics skill's own per-issue rows, and renders each Epic's recorded outcome or says plainly that none is recorded and asks the team for one. Read-only -- never transitions, comments, creates, updates or deletes Jira data, and writes no file that survives the run. Do NOT use for team-level flow metrics (that is flow-metrics), for sprint readiness or pick-up routing, or for any tracker that is not Jira.
- ▌ Code Intelligence · eugenelim bundleUse when a question is about what is true in a codebase rather than what to change — locate a symbol, explain a class or service, find callers and callees, trace dependencies, work out the blast radius of a change, assemble bounded context for a task, find hotspots or architectural clusters, or inspect lineage and business rules. Triggers on "what calls this", "what breaks if I change X", "how does X actually work", "where is X implemented", "what depends on X", "map this codebase", "what are the hotspots here", "is this dead code", "trace this dependency". Answers from an indexed code graph and preserves the confidence, provenance, and unresolved-edge counts that index reports. Do NOT use to decide what a change should be — that belongs to whichever workflow skill asked the question.
- ▌ Repository Grounding · eugenelim bundleUse this skill to answer "what already governs these paths?" before writing a spec, plan, or implementation. Probes the paths a change will touch and reports governing files, references, phrase pins, gates, co-change partners, and dead links — selected by stage. Use it at discovery to orient before authoring and at review to check what the authored artifacts reference. It can add attributed evidence from an already-exposed code-intelligence capability, but never needs one. Do NOT use it to install, index, or refresh a provider, or for any inquiry that mutates repository state.
- ▌ Repository Exploration · eugenelim bundleUse this skill when a workflow step or a user needs bounded, attributed repository evidence to settle a pending decision — which files a plan must touch, whether a rename or removal is safe, where a bad value enters before a fix, or whether a fix reaches a live code path. It owns that inquiry for the caller. It records the question and stopping rule, uses an already-exposed capability only when its native action fits, otherwise answers from repository search, and checks load-bearing claims against source. The caller keeps the decision, and no provider is required. Do NOT use it to plan, build, or fix the change itself — the calling workflow owns that. Route path-seeded "what governs these paths?" questions to repository-grounding instead.
- ▌ Intent · eugenelim bundleUse when shaping a piece of product work before it becomes a spec. Three modes: `frame` turns a rough idea, request, or strategy into a level-tagged intent: the problem, who has it, the outcome, and the opportunity behind it; `de-risk` finds the assumption that would sink an intent if it were wrong and picks a cheap test for it, with a kill condition set in advance; `decompose` breaks a surviving intent into child intents or a delivery contract. Triggers on "shape this", "frame the problem", "de-risk this", "test the bet", "what's the riskiest assumption", "how do we test this cheaply", "break this down", "slice this". Route mode applies only when the user asks which way to shape something: it names the short, longer, or supervised route. Shows where you are on the intent lifecycle and offers the next step. Do NOT use only to record an outcome the user has already stated (use `intake-intent`), to write a spec (use `new-spec`), or to read a raw market signal (use `frame-situation`).
- ▌ Explain Diff · eugenelim bundleUse this skill when a user asks for a self-contained explanation of how a local code diff, branch, commit, or pull-request representation works. It traces the changed code and nearby tests, designs a work-specific offline HTML lesson, publishes it through the bundled standard-library publisher, and reports the exact file path. Do NOT use for correctness review, bug fixing, generic document conversion, product UI implementation, or visual QA.
- ▌ Navigate Intents · eugenelim bundleUse this skill when asked to look up, trace, explore, or summarise product intents, to find outstanding work placed under its parent intent, or to export them as offline HTML. Triggers on phrases like "show me intent:my-slug", "which intents are accepted", "trace the parent of this intent", "find outstanding intents", "intent graph", "intent hierarchy", "show me outstanding work", "what are the children of this capability". For a brief or spec question, use `outstanding` to see placed items or `record` on the parent intent — `--id` and `--from` resolve only live intents. Do NOT use for queue order ("what's next") — use `work-loop`'s `dispatch.py`. Do NOT use for workspace repair — use `workspace-status`. Do NOT use for ADR or RFC lookups, ADR or RFC HTML views, or "how many roadmap intents do we have" — use `navigate-decisions` (repo-governance pack); for ADR or RFC authoring use `new-adr`/`new-rfc`. Do NOT use for creating, de-risking, decomposing, or closing intents — use `work-intake` or `close-work`.
- ▌ Navigate Decisions · eugenelim bundleUse this skill to look up, summarise, trace, explore or health-check architecture decision records (ADRs) and RFCs, or route a decision. Triggers on "show me ADR-0001", "which ADRs are accepted", "what supersedes this decision", "trace the lineage of RFC-0042", "find decisions about authentication", "rfc status", "show me the RFC landscape", "how many RFCs are in draft", "any RFC candidates in the findings register", "rfc report", "how many roadmap intents do we have", "export the decision corpus to HTML". In route mode, "which record does this decision need", "how should we decide this", "who should I consult about this decision", "is this decision a one-way door". In health mode, "which decisions are due or stale", "superseded ADRs still cited", "missing confirmation checks". Do NOT use for creating or revising records (use `new-adr` or `new-rfc`). Do NOT use when the user already wants to propose, reopen or circulate a direction (use `new-rfc`). Do NOT use for intent-hierarchy or intent-status queries.
- ▌ Github Pr · eugenelim bundleUse for a GitHub pull request in one of three modes. Review someone else's PR ("review PR 42", "look over this pull request"), iterate on your own PR's feedback and failing checks ("iterate on PR 42", "address the feedback on my PR", "why is CI red on my PR"), or adopt a contributor's PR and carry it to merge ("adopt this contributor's PR", "take over PR 42 and merge it"). Changes nothing until you approve the exact action list or adoption contract. Not for opening a PR, auto-merge, or Azure DevOps.
- ▌ Bug Fix 2 · eugenelim bundleUse this skill when the user wants to diagnose or fix a deviation between current and intended behavior in existing code -- including requests to find the root cause, explain a CI-only failure, investigate intermittent or flaky behavior, or contain and diagnose a production incident. Triggers on "fix bug", "diagnose and fix", "find the root cause", "why does this fail", "investigate this regression", and "this is broken". Do NOT use for new features, behavior-preserving refactors, postmortems, or skill maintenance; use the repository's planning workflow instead.
- ▌ New Adr 2 · eugenelim bundleUse this skill when the user asks to create, write, draft, or open a new ADR (architecture decision record). Triggers on phrases like "new ADR", "write an ADR for...", "record this decision", "let's ADR this". Do NOT use for RFCs (use `new-rfc`) or feature specs (use `new-spec`).
- ▌ New Rfc 2 · eugenelim bundleUse this skill when the user asks to propose, draft, or open an RFC, update the rules, amend the charter, change our principles, or change the convention for something; also use it for follow-on RFC artifacts after acceptance. Triggers on "RFC", "propose a change to...", "let's get input on...", "draft a proposal", "create the follow-on specs for RFC-NNNN", "generate ADRs for the accepted RFC", and "implement the follow-on work from an RFC". Do NOT use for a settled architectural decision (use `new-adr`, including a superseding ADR), or for a standalone settled feature spec (use `new-spec`).
- ▌ New Spec 2 · eugenelim bundleUse this skill when the user wants to start a new feature with a spec, or wants to write a spec for something they're about to build. Triggers on "new spec", "write a spec for X", "let's spec this out", "start a feature for...". Spec-driven development; the spec drives implementation. Do NOT use for cross-cutting proposals (use `new-rfc`) or recording decisions (use `new-adr`).
- ▌ Work Loop 2 · eugenelim bundleUse when implementing or resuming a non-trivial repository change: a feature, behavior-changing fix, refactor, migration, framework or dependency upgrade, schema or API change, performance work, infrastructure or build-system change, reversion, or an existing build spec under `docs/specs/`. Also use for bare continuation commands ('resume', 'continue', 'keep going', 'pick up where I left off', 'let's get going') when conversation or workspace context identifies active build work. Do not use for shaping, research, strategy, product planning, design exploration, monitoring or status-only work, review-only, explanation-only, specification-authoring-only, spike-only or throwaway exploration, or trivial edits that are cosmetic, tightly local, behavior-preserving, and have obvious verification.
- ▌ Close Work 2 · eugenelim bundleUse when completed, abandoned, or superseded delivery work needs closeout, durable-context verification, initiative reconciliation, pause handling, or a safe immediate-disposition preview.
- ▌ Rfc Status 2 · eugenelim bundleSurface the current RFC landscape at a glance — how many RFCs are in each lifecycle state, which are active, and how many findings are waiting in the candidate register. Triggers on 'rfc status', 'show rfcs', 'what rfcs are open', 'rfc dashboard', 'how many rfcs', 'rfc candidates', 'rfc report', or any request for an overview of the RFC landscape. Read-only: never creates or modifies RFC files.
- ▌ Compile Okf 2 · eugenelim bundleUse when a catalogue maintainer needs to compile declared OKF authoring bundles into generated router and reviewed procedure Skills, or check that committed generated output is current.
- ▌ Work Intake 2 · eugenelim bundleUse for a raw or ambiguous work request, source acquisition or refresh, generic intake-safety handling, or an older compatibility alias. Explicit status, artifact, skill, product-shaping, architecture-design, and defect requests route directly to their owners.
- ▌ Author Brief 2 · eugenelim bundleDeprecated compatibility alias for author-delivery-brief create. Use only when an older caller explicitly invokes author-brief.
- ▌ Capture Work 2 · eugenelim bundleUse this compatibility skill when the user asks to capture, queue, remember, or add follow-up work for later. Prefer work-intake for new usage; this name remains active only to route older capture-work prompts to the canonical intake surface.
- ▌ Init Project 2 · eugenelim bundleUse this skill to turn an idea into a structured new repo. It runs a trigger gate (throwaways and single scripts skip it), a value gate over fed-in discovery, records a foundation (an ADR plus a reference.md golden path), authors a walking-skeleton spec via new-spec and hands the build to work-loop, then hands off to the normal build loop. Triggers on "start a new project", "greenfield init", "idea to repo", "bootstrap a new codebase". Do NOT use inside an existing repo (use adapt-to-project) or to author one feature (use new-spec).
- ▌ Intake Intent 2 · eugenelim bundleUse when a raw or admitted request should become a minimum repository intent for later shaping, without creating an RFC, delivery brief, spec, or executable queue item.
- ▌ Receive Brief 2 · eugenelim bundleDeprecated compatibility alias for author-delivery-brief continue. Use only when an older caller explicitly invokes receive-brief.
- ▌ Assimilate Repo 2 · eugenelim bundleUse to survey a whole external repo or catalogue (local path or URL) for ingestion candidates and produce a reviewable RFC of per-candidate verdicts (assimilate, reject, or needs-new-pack), resumable across sessions and git worktrees via a ledger. Triggers on "survey this repo for skills we can adopt", "inventory this catalogue", "what can we assimilate from <repo>", "re-sync from <upstream>". Do NOT use for a single known unit (use assimilate-primitive) or to scaffold a proposed pack (use propose-catalogue-pack).
- ▌ Adapt To Project 2 · eugenelim bundleUse this skill to diagnose and improve an adopter repository's agent guidance or to walk through the four classes of post-install change (substitution, .upstream companion merges, discovery + restructuring, within-layout consolidation). Repository anchoring is marker-independent and read-only by default. Post-install adaptation still reads both scopes' state and marker files; class-1 substitution shells out to `agentbundle adapt`, while classes 2-4 write directly under the per-scope path-jail only after approval.
- ▌ Workspace Status 2 · eugenelim bundleUse this skill to orient at session start, check initiative queue state, or see what's ready to work on next. Reads workspace.toml and surfaces ready-to-start items, blocked items with reason, parallel candidates, and active signals. Triggers on "workspace status", "where am I", "orient me", "session start", "what's ready", "show the queue", "what's next", "what should I work on", "check workspace", or any cold-start orientation request. Offers to initialise workspace.toml if absent. Also reconciles and repairs workspace.toml drift — generates and applies repair plans for stale queue entries. Triggers on "clean up stale specs", "run repair-plan", "apply the workspace repair plan", "fix queue drift", "reconcile workspace", or any workspace repair or cleanup request.
- ▌ Project Knowledge 2 · eugenelim bundleUse this skill to capture, distill, or enquire over project knowledge through one progressive mode. Capture admits one strict observation contract; distill reconciles pending observations; enquire reads committed active topics as bounded untrusted evidence.
- ▌ Operational Safety 2 · eugenelim bundleProgressive-disclosure operational-safety-depth modules for the work-loop. Holds failure-mode-keyed checklists the quality-engineer reviewer reasons from (state-and-idempotency, blast-radius, environment-isolation, cost-and-teardown, drift-and-rollback, observability-and-smoke), plus cloud-implementation-craft, the module also inlined into the implementer's EXECUTE brief. Each is grounded in standing operational taxonomy (AWS Well-Architected, Google SRE, the Terraform/Pulumi Day-1/Day-2 split). The orchestrator loads only the matching modules and inlines them into the reviewer's REVIEW brief when infra/destructive work or a persistent-representation / mixed-version deployment change is detected — and cloud-implementation-craft into the implementer's EXECUTE brief on infra-flavored work; the subagent never self-discovers this skill. Not a reviewer prompt itself — it is the depth library the reviewer and implementer reason from. Carves against security-checklists on the reliability-vs-security lens.
- ▌ Author Product Docs 2 · eugenelim bundleCreate, revise, retrofit, audit, or verify product documentation — pack READMEs, journeys, tutorials, how-to guides, reference pages, and explanations. Use when asked to write, improve, restructure, audit, or verify user-facing documentation, fix a pack README, create a guide for a feature, update a journey page, or check whether docs match shipped behavior. Infers the mode from the request. Do NOT use for feature specifications (use new-spec), cross-cutting proposals (use new-rfc), decisions (use new-adr), product or market strategy, frontend implementation alone, internal maintainer runbooks without user-facing concern, or arbitrary prose editing with no documentation purpose.
- ▌ Security Checklists 2 · eugenelim bundleProgressive-disclosure security-depth modules for the security-reviewer. Holds boundary-keyed checklists (access-control, authn-session, injection, path-and-file, secrets-and-crypto, outbound-ssrf, supply-chain, config-misconfig, exceptional-conditions, llm-agent, agentic-skills) as references/, each anchored on a current standard (OWASP Top 10:2025, ASVS 5.0, API Security Top 10:2023, Proactive Controls 2024, CWE Top 25, OWASP LLM Top 10:2025, OWASP Top 10 for Agentic Applications:2026, OWASP Agentic Skills Top 10 v1.0 (AST01–AST10)). The work-loop's orchestrator loads only the boundary-matching modules and inlines them into the security-reviewer's brief; the subagent never self-discovers this skill. Not a reviewer prompt itself — it is the depth library the reviewer reasons from.
- ▌ Assimilate Primitive 2 · eugenelim bundleUse to bring a single external agent primitive — one skill, subagent, hook, or command (or a small connected bundle) — from a local path or URL into this catalogue. Fetches it, diagnoses the destination pack and lifecycle from the local charter, and migrates it to pack convention, or rejects it with a reason. Triggers on "assimilate this skill from <path/url>", "bring in this agent", "adopt this hook into a pack". Do NOT use to survey a whole repo (use assimilate-repo) or to justify a new pack (use propose-catalogue-pack).
- ▌ Contract Acquisition 2 · eugenelim bundleAcquire a platform's or library's real contract from its own toolchain oracles before authoring against an unfamiliar one — infrastructure, a CLI invocation, code on a managed runtime, or code against an unfamiliar framework or third-party library whose contract you don't hold. Triggers on "deploy to", "write the Terraform / Pulumi / CDK for", "provision", "what's the right resource shape", "why does this apply fail", "what's the signature / does this still exist in this version", "why does this library call raise". Runs a tiered, tool-keyed protocol — detect the stack or library + version, run the toolchain's validate / plan / synth or the type-checker / compiler + API-surface oracle, consult a curated skill, retrieve versioned docs, then a runtime probe — declares its oracle tier and degrades honestly to the probe when no strong static oracle exists. Do NOT use for code whose contract you already hold (use work-loop directly), nor to review a finished diff (rides quality-engineer).
- ▌ Author Delivery Brief 2 · eugenelim bundleUse with an explicit create or continue mode to author a Draft delivery brief from a coherent multi-slice or cross-repository outcome, or to review an existing repository brief for Ready and select confirmed delivery slices.
- ▌ Propose Catalogue Pack 2 · eugenelim bundleUse to justify and scaffold a NEW pack area for this catalogue — test that it is additive and fits the target catalogue's declared coverage model and applicable Charter admission path, then scaffold the pack shell and emit an RFC with a per-primitive inventory, or reject it as non-additive. Triggers on "should we add a pack for <area>", "propose a new pack", "justify a <vendor/domain> pack". Do NOT use to ingest units (use assimilate-primitive or assimilate-repo).
- ▌ Security Checklists Reference 2 · eugenelim bundleRoute into the compiled OKF bundle `security-checklists` using generated indexes.
- ▌ Example Skill 3 · eugenelim bundleDemonstrate the standard skill layout. Triggers on: run example, show example skill output. Near-miss: requesting a demo or test of any skill (route those to the specific skill).
- ▌ Bug Fix · eugenelim bundleUse this skill when the user wants to diagnose or fix a deviation between current and intended behavior in existing code -- including requests to find the root cause, explain a CI-only failure, investigate intermittent or flaky behavior, or contain and diagnose a production incident. Triggers on "fix bug", "diagnose and fix", "find the root cause", "why does this fail", "investigate this regression", and "this is broken". Do NOT use for new features, behavior-preserving refactors, postmortems, or skill maintenance; use the repository's planning workflow instead.
- ▌ New Adr · eugenelim bundleUse this skill when the user asks to create, write, draft, or open a new ADR (architecture decision record). Triggers on phrases like "new ADR", "write an ADR for...", "record this decision", "let's ADR this". Do NOT use for RFCs (use `new-rfc`) or feature specs (use `new-spec`).
- ▌ New Rfc · eugenelim bundleUse this skill when the user asks to propose, draft, or open an RFC, update the rules, amend the charter, change our principles, or change the convention for something; also use it for follow-on RFC artifacts after acceptance. Triggers on "RFC", "propose a change to...", "let's get input on...", "draft a proposal", "create the follow-on specs for RFC-NNNN", "generate ADRs for the accepted RFC", and "implement the follow-on work from an RFC". Do NOT use for a settled architectural decision (use `new-adr`, including a superseding ADR), or for a standalone settled feature spec (use `new-spec`).
- ▌ New Spec · eugenelim bundleUse this skill when the user wants to start a new feature with a spec, or wants to write a spec for something they're about to build. Triggers on "new spec", "write a spec for X", "let's spec this out", "start a feature for...". Spec-driven development; the spec drives implementation. Do NOT use for cross-cutting proposals (use `new-rfc`) or recording decisions (use `new-adr`).
- ▌ Work Loop · eugenelim bundleUse when implementing or resuming a non-trivial repository change: a feature, behavior-changing fix, refactor, migration, framework or dependency upgrade, schema or API change, performance work, infrastructure or build-system change, reversion, or an existing build spec under `docs/specs/`. Also use for bare continuation commands ('resume', 'continue', 'keep going', 'pick up where I left off', 'let's get going') when conversation or workspace context identifies active build work. Do not use for shaping, research, strategy, product planning, design exploration, monitoring or status-only work, review-only, explanation-only, specification-authoring-only, spike-only or throwaway exploration, or trivial edits that are cosmetic, tightly local, behavior-preserving, and have obvious verification.
- ▌ Close Work · eugenelim bundleUse when completed, abandoned, or superseded delivery work needs closeout, durable-context verification, initiative reconciliation, pause handling, or a safe immediate-disposition preview.
- ▌ Rfc Status · eugenelim bundleSurface the current RFC landscape at a glance — how many RFCs are in each lifecycle state, which are active, and how many findings are waiting in the candidate register. Triggers on 'rfc status', 'show rfcs', 'what rfcs are open', 'rfc dashboard', 'how many rfcs', 'rfc candidates', 'rfc report', or any request for an overview of the RFC landscape. Read-only: never creates or modifies RFC files.
- ▌ Compile Okf · eugenelim bundleUse when a catalogue maintainer needs to compile declared OKF authoring bundles into generated router and reviewed procedure Skills, or check that committed generated output is current.
- ▌ Work Intake · eugenelim bundleUse for a raw or ambiguous work request, source acquisition or refresh, generic intake-safety handling, or an older compatibility alias. Explicit status, artifact, skill, product-shaping, architecture-design, and defect requests route directly to their owners.
- ▌ Author Brief · eugenelim bundleDeprecated compatibility alias for author-delivery-brief create. Use only when an older caller explicitly invokes author-brief.
- ▌ Capture Work · eugenelim bundleUse this compatibility skill when the user asks to capture, queue, remember, or add follow-up work for later. Prefer work-intake for new usage; this name remains active only to route older capture-work prompts to the canonical intake surface.
- ▌ Init Project · eugenelim bundleUse this skill to turn an idea into a structured new repo. It runs a trigger gate (throwaways and single scripts skip it), a value gate over fed-in discovery, records a foundation (an ADR plus a reference.md golden path), authors a walking-skeleton spec via new-spec and hands the build to work-loop, then hands off to the normal build loop. Triggers on "start a new project", "greenfield init", "idea to repo", "bootstrap a new codebase". Do NOT use inside an existing repo (use adapt-to-project) or to author one feature (use new-spec).
- ▌ Intake Intent · eugenelim bundleUse when a raw or admitted request should become a minimum repository intent for later shaping, without creating an RFC, delivery brief, spec, or executable queue item.
- ▌ Receive Brief · eugenelim bundleDeprecated compatibility alias for author-delivery-brief continue. Use only when an older caller explicitly invokes receive-brief.
- ▌ Figma · eugenelim bundleRead and inspect Figma files (Cloud) via the REST API. Supports fetching files / specific nodes / file metadata / version history / comments, rendering frames to PNG/SVG/JPG/PDF, posting comments (file-level or pinned to a node), converting FigJam connector graphs to Mermaid, and best-effort reads of design tokens (variables) and dev resources where the token's plan allows. Use when the user wants to read, render, comment on, or extract structure from a Figma file. Does NOT modify design content -- that requires the Figma Plugin API, not REST.
- ▌ Assimilate Repo · eugenelim bundleUse to survey a whole external repo or catalogue (local path or URL) for ingestion candidates and produce a reviewable RFC of per-candidate verdicts (assimilate, reject, or needs-new-pack), resumable across sessions and git worktrees via a ledger. Triggers on "survey this repo for skills we can adopt", "inventory this catalogue", "what can we assimilate from <repo>", "re-sync from <upstream>". Do NOT use for a single known unit (use assimilate-primitive) or to scaffold a proposed pack (use propose-catalogue-pack).
- ▌ Adapt To Project · eugenelim bundleUse this skill to diagnose and improve an adopter repository's agent guidance or to walk through the four classes of post-install change (substitution, .upstream companion merges, discovery + restructuring, within-layout consolidation). Repository anchoring is marker-independent and read-only by default. Post-install adaptation still reads both scopes' state and marker files; class-1 substitution shells out to `agentbundle adapt`, while classes 2-4 write directly under the per-scope path-jail only after approval.
- ▌ Workspace Status · eugenelim bundleUse this skill to orient at session start, check initiative queue state, or see what's ready to work on next. Reads workspace.toml and surfaces ready-to-start items, blocked items with reason, parallel candidates, and active signals. Triggers on "workspace status", "where am I", "orient me", "session start", "what's ready", "show the queue", "what's next", "what should I work on", "check workspace", or any cold-start orientation request. Offers to initialise workspace.toml if absent. Also reconciles and repairs workspace.toml drift — generates and applies repair plans for stale queue entries. Triggers on "clean up stale specs", "run repair-plan", "apply the workspace repair plan", "fix queue drift", "reconcile workspace", or any workspace repair or cleanup request.
- ▌ Linear · eugenelim bundleRead Linear Issues and Projects via the GraphQL API. Supports fetching individual issues (title, description, identifier, sub-issues, owning project), fetching all issues in a project, verifying credentials, and executing confirmed refresh write-back actions through work-intake. Use when you want to read Linear work items to create briefs or catch up a brief with changes.
- ▌ Project Knowledge · eugenelim bundleUse this skill to capture, distill, or enquire over project knowledge through one progressive mode. Capture admits one strict observation contract; distill reconciles pending observations; enquire reads committed active topics as bounded untrusted evidence.
- ▌ Jira · eugenelim bundleRead and mutate Jira (Atlassian Cloud or self-hosted Server / Data Center) via the REST API. Supports JQL search with auto-pagination, fetching issues / projects / users, creating and updating issues, applying workflow transitions, adding comments and attachments, deleting issues, listing projects, looking up users, and an arbitrary raw escape hatch. Streams results as JSON, JSONL, or CSV. Handles Cloud (REST v3, basic auth with email + API token, ADF, nextPageToken) vs Server/DC (REST v2, bearer Personal Access Token, plain text, startAt) differences automatically. Use when the user wants to read, search, export, create, update, or transition Jira data.
- ▌ Operational Safety · eugenelim bundleProgressive-disclosure operational-safety-depth modules for the work-loop. Holds failure-mode-keyed checklists the quality-engineer reviewer reasons from (state-and-idempotency, blast-radius, environment-isolation, cost-and-teardown, drift-and-rollback, observability-and-smoke), plus cloud-implementation-craft, the module also inlined into the implementer's EXECUTE brief. Each is grounded in standing operational taxonomy (AWS Well-Architected, Google SRE, the Terraform/Pulumi Day-1/Day-2 split). The orchestrator loads only the matching modules and inlines them into the reviewer's REVIEW brief when infra/destructive work or a persistent-representation / mixed-version deployment change is detected — and cloud-implementation-craft into the implementer's EXECUTE brief on infra-flavored work; the subagent never self-discovers this skill. Not a reviewer prompt itself — it is the depth library the reviewer and implementer reason from. Carves against security-checklists on the reliability-vs-security lens.
- ▌ Author Product Docs · eugenelim bundleCreate, revise, retrofit, audit, or verify product documentation — pack READMEs, journeys, tutorials, how-to guides, reference pages, and explanations. Use when asked to write, improve, restructure, audit, or verify user-facing documentation, fix a pack README, create a guide for a feature, update a journey page, or check whether docs match shipped behavior. Infers the mode from the request. Do NOT use for feature specifications (use new-spec), cross-cutting proposals (use new-rfc), decisions (use new-adr), product or market strategy, frontend implementation alone, internal maintainer runbooks without user-facing concern, or arbitrary prose editing with no documentation purpose.
- ▌ Security Checklists · eugenelim bundleProgressive-disclosure security-depth modules for the security-reviewer. Holds boundary-keyed checklists (access-control, authn-session, injection, path-and-file, secrets-and-crypto, outbound-ssrf, supply-chain, config-misconfig, exceptional-conditions, llm-agent, agentic-skills) as references/, each anchored on a current standard (OWASP Top 10:2025, ASVS 5.0, API Security Top 10:2023, Proactive Controls 2024, CWE Top 25, OWASP LLM Top 10:2025, OWASP Top 10 for Agentic Applications:2026, OWASP Agentic Skills Top 10 v1.0 (AST01–AST10)). The work-loop's orchestrator loads only the boundary-matching modules and inlines them into the security-reviewer's brief; the subagent never self-discovers this skill. Not a reviewer prompt itself — it is the depth library the reviewer reasons from.
- ▌ Assimilate Primitive · eugenelim bundleUse to bring a single external agent primitive — one skill, subagent, hook, or command (or a small connected bundle) — from a local path or URL into this catalogue. Fetches it, diagnoses the destination pack and lifecycle from the local charter, and migrates it to pack convention, or rejects it with a reason. Triggers on "assimilate this skill from <path/url>", "bring in this agent", "adopt this hook into a pack". Do NOT use to survey a whole repo (use assimilate-repo) or to justify a new pack (use propose-catalogue-pack).
- ▌ Contract Acquisition · eugenelim bundleAcquire a platform's or library's real contract from its own toolchain oracles before authoring against an unfamiliar one — infrastructure, a CLI invocation, code on a managed runtime, or code against an unfamiliar framework or third-party library whose contract you don't hold. Triggers on "deploy to", "write the Terraform / Pulumi / CDK for", "provision", "what's the right resource shape", "why does this apply fail", "what's the signature / does this still exist in this version", "why does this library call raise". Runs a tiered, tool-keyed protocol — detect the stack or library + version, run the toolchain's validate / plan / synth or the type-checker / compiler + API-surface oracle, consult a curated skill, retrieve versioned docs, then a runtime probe — declares its oracle tier and degrades honestly to the probe when no strong static oracle exists. Do NOT use for code whose contract you already hold (use work-loop directly), nor to review a finished diff (rides quality-engineer).
- ▌ Author Delivery Brief · eugenelim bundleUse with an explicit create or continue mode to author a Draft delivery brief from a coherent multi-slice or cross-repository outcome, or to review an existing repository brief for Ready and select confirmed delivery slices.
- ▌ Propose Catalogue Pack · eugenelim bundleUse to justify and scaffold a NEW pack area for this catalogue — test that it is additive and fits the target catalogue's declared coverage model and applicable Charter admission path, then scaffold the pack shell and emit an RFC with a per-primitive inventory, or reject it as non-additive. Triggers on "should we add a pack for <area>", "propose a new pack", "justify a <vendor/domain> pack". Do NOT use to ingest units (use assimilate-primitive or assimilate-repo).
- ▌ Jira Align · eugenelim bundleRead and mutate Jira Align (Atlassian Cloud or self-hosted/on-prem) via the REST API 2.0. Supports fetching individual records (epics, features, stories, capabilities, themes, portfolios, programs, teams, users, etc.), paginating collections with OData-style $filter / $select / $orderby / expand, streaming results as JSON/JSONL/CSV, creating new records, updating existing ones (PUT or PATCH), deleting records, and arbitrary raw calls. Use when the user wants to read, search, export, create, or update Jira Align data.
- ▌ Github Refresh · eugenelim bundleReviewed refresh and confirmed GitHub coordination write-back processor for tracker-origin artifacts.
- ▌ Flow Metrics · eugenelim bundleUse this skill when the user asks for DORA / Flow Framework metrics over a Jira scope -- "what's our cycle time this quarter for PROJ", "give me throughput and WIP for the Foo team", "compare flow efficiency before/after the AI-pairing rollout via a cohort split", "rollup flow metrics across program 42". Computes cycle time, lead time, throughput, WIP, flow load, rework rate, flow efficiency, flow distribution, and defect ratio from Jira changelogs (optionally joined with Jira Align for program / portfolio scope). Read-only -- never transitions, comments, creates, updates, or deletes Jira data. Do NOT use for live-dashboard streaming, deployment-event metrics (Change Failure Rate / MTTR proper), or anything requiring a tracker that isn't Jira.
- ▌ Jira Refresh · eugenelim bundleReviewed refresh and confirmed Jira coordination write-back processor for tracker-origin artifacts.
- ▌ API Contract · eugenelim bundleUse when generating an OpenAPI 3.1 API contract from requirements, user stories, or domain models. Applies a pluggable API standard (Zalando by default) as hard constraints to produce complete, validated YAML specs ready for code gen, test gen, mocks, and SDKs. Activate for tasks involving API design, REST contract authoring, or OpenAPI spec creation.
- ▌ Render Proof · eugenelim bundleRender a Markdown file as a self-contained, offline HTML proof artifact styled for human review. Use when the user asks to "render this for review", "proof this draft", "give me a proof of this document", "show me this markdown rendered", or "make this readable for a reviewer". Outputs a single HTML file that opens in any browser with no server or network access at view time. Not for slides, presentations, or publication — use markdown-to-html for that. The rendered output uses a muted stone/slate palette deliberately distinct from the publication look.
- ▌ Event Contract · eugenelim bundleUse when authoring an AsyncAPI event contract from requirements, user stories, or domain models. Applies a pluggable event-design standard (Zalando by default) as hard constraints and composes a swappable message envelope (CloudEvents by default) to produce a complete, validated AsyncAPI document for an event stream you produce or own. Activate for event-driven API design, event/message contract authoring, or AsyncAPI spec creation. Author only when the feature produces or owns the event type, not when it merely consumes one.
- ▌ Source Map · eugenelim bundleCurate the authoritative sources for a topic before research begins. Surveys adjacent material to discover voices rather than asking the LLM directly who's authoritative — STORM's finding is that direct question-asking does not work well for source discovery. Produces `<topic-slug>-sources.md` grouping candidates by primacy (`primary` / `secondary` / `tertiary`). When invoked downstream of `/identify-perspectives`, groups sources by camp; in standalone invocations, skips the camp-grouping step. Depth cues — `quickly`, `top three`, `briefly`, `summary only` for narrow surveys; `comprehensively`, `exhaustively`, `in depth`, `extensive` for thorough ones.
- ▌ Linear Brief Sync · eugenelim bundleUse this compatibility skill when you want to catch up an existing product brief with changes in the linked Linear Issue — "sync the brief with LIN-123", "the Linear issue has been updated, update the brief". It delegates refresh authority, lifecycle checks, and write-back confirmations to the configured `work-intake` Linear refresh processor while preserving the old trigger language.
- ▌ Run Swot · eugenelim bundleUse when a strategist needs a structured situation synthesis before committing to a strategic direction. Triggers on "run a SWOT", "I need to understand our position", "situation synthesis before setting strategy", "what are our strengths and weaknesses", "map out opportunities and threats". Produces a committed SWOT artifact. Do NOT use as a substitute for market data — SWOT organizes what you know; it does not generate evidence you don't have.
- ▌ Security Checklists Reference · eugenelim bundleRoute into the compiled OKF bundle `security-checklists` using generated indexes.
- ▌ Architect Assess · eugenelim bundleUse when the user wants to understand, assess, harden, optimize, scale, modernize, rationalize, replace, or plan action for the architecture that exists in a repository or implemented system. Routes the generic request "assess architecture and provide an action plan" here. Builds a correctable current-state model, evidence coverage, an attention heat map, bounded hotspot drill-downs, findings, and dependency-aware action waves. Do NOT use for a future-state design choice (architect-design), a diagram as the main ask (architect-diagram), or critique of a supplied artifact (architect-review).
- ▌ Architect Design · eugenelim bundleUse when the user is framing a problem, weighing a technical choice, or designing a system or integration without a diagram as the headline ask. Triggers on "how should we", "we need to", "what's the right way to build X", tech-selection, integration design, NFR trade-offs. Shapes a one-page concept first, then produces a Google-style design doc (TL;DR, context, goals/non-goals, proposal, alternatives, risks, rollout, open questions), 2-5 pages, with Mermaid inline, and converges it against review. Cloud well-architected by construction (AWS/Azure/GCP and primitives providers like Hetzner). Do NOT use when the ask is a diagram (use `architect-diagram`) or a critique (use `architect-review`).
- ▌ Architect Review · eugenelim bundleUse when the user supplies an architecture artifact (assessment report, design doc, diagram, RFC, ADR) and asks for critique. Triggers on "review this", "what's wrong with", "is this any good", or any artifact-shaped paste with a question attached. Produces a verdict (SHIP IT / SHIP WITH CHANGES / MAJOR REWRITE / WRONG ARTIFACT), executive summary, severity-tagged findings, and a closing "what's working" section. Also runs a well-architected / lens review mode (concern + workload-class lenses incl. GenAI/agentic) emitting a risk register with mechanical/judgment-tagged findings. Renders inline by default; saves only on an explicit user request naming the destination. Do NOT assess a repository, produce an artifact, or redesign the system.
- ▌ Jira Defect Flow · eugenelim bundleUse this skill when the user points at a Jira defect and asks you to handle it end-to-end -- "fix PROJ-123", "work this bug ticket", "diagnose and ship a fix for this defect". The skill pulls the ticket via the `jira` skill, hands the actual fix to the `bug-fix` skill (reproduction-first, root-cause, minimum-diff, regression-test), opens a PR whose body links back to Jira, and comments + transitions the ticket. By default it stops at PR-opened; runs a dev-deploy step only if the consumer repo provides one. Do NOT use for stories, tasks, or feature work -- those go through `new-spec`.
- ▌ Jira Team Status · eugenelim bundleTeam backlog status for sprint, stand-up, and orientation — what the team can pick up, what is ready, blocked, in progress, unassigned, stale, or needs story work. Triggers on "show me the team backlog", "what can the team pick up", "what is ready", "what is blocked", "what is unassigned", "sprint status", "stand-up summary", "stale team work". Applies the five-question bar only when explicitly asked for agent-ready or one-PR work. Always start read-only; disclose scope and completeness. Do NOT use to improve weak stories (use jira-story-triage), create an issue (use jira), apply approved updates (use jira), turn an epic into specs (use jira-brief-intake), fix a defect end-to-end (use jira-defect-flow), or for the local workspace queue (use workspace-status).
- ▌ Msg To Markdown · eugenelim bundleConvert Outlook .msg and MIME .eml email files to Markdown with a versioned output contract, preserving headers (From, To, CC, BCC, Date, Importance), the body (HTML reduced to Markdown, or plain text), and an attachments table. Use when the user wants to convert, read, or process a .msg or .eml email into Markdown, or extract its attachments.
- ▌ Github Brief Intake · eugenelim bundleUse when GitHub work should enter the repository work-intake route, including an Issue, Milestone, view, or cross-repository selection.
- ▌ Generate Iac · eugenelim bundleUse this skill to author governed, best-practice Terraform/OpenTofu infrastructure from a plain-language intent. Triggers on "provision X", "create Terraform for", "generate IaC for", "set up cloud resources", "write Terraform for", "scaffold infrastructure". Stops at a digest-pinned `terraform plan` (G4 handoff); never runs `apply`. Governance-first — resolves the decision-record surface before any code.
- ▌ Linear Brief Intake · eugenelim bundleUse when Linear work should enter the repository work-intake route, including an Issue, sub-issues, a Project, Cycle, view, or cross-repository selection.
- ▌ Architect Diagram · eugenelim bundleUse when the user asks for a diagram of a system, integration, flow, state, data model, deployment topology, roadmap, prioritization matrix, or decomposition. Triggers on "show me", "draw", "diagram of", or artifact-shaped nouns like "sequence", "C4 Container view", "state machine", "roadmap", "2×2", "mind map", "branching strategy", "gantt", "sprint plan". Produces Mermaid diagrams (flowchart, sequenceDiagram, C4, stateDiagram-v2, erDiagram, gitGraph, gantt, plus timeline, quadrantChart, and mindmap for roadmaps, prioritization, and hierarchical decomposition) routed by intent. Cloud-aware (AWS, Azure, GCP, and primitives providers like Hetzner) and agentic-platform-aware (Bedrock AgentCore, AI Foundry, Vertex Agent Engine). Do NOT use for full design-doc drafting (use `architect-design`), critique (use `architect-review`), or comparison tables (use plain Markdown).
- ▌ Jira Brief Intake · eugenelim bundleUse when Jira work should enter the repository work-intake route, whether the selection is one issue, an epic, a board, a sprint, or JQL.
- ▌ Jira Story Triage · eugenelim bundleReview Jira work items for readiness and improve weak stories — it explains why each item is not ready (which question failed and the specific gap), identifies unresolved human questions, drafts proposed rewrites and acceptance criteria, and writes to Jira only after you approve the exact payload; read-only until then. Triggers on "which stories are not ready", "which stories need more detail", "improve these weak stories", "make these tickets actionable", "draft better acceptance criteria", "apply the story-readiness bar", "explain why these items are not ready", "prepare Jira story improvements without writing". Do NOT use for a read-only team status snapshot or what to pick up next / blocked / unassigned / in progress / stand-up (use jira-team-status), to create an issue (use jira), to apply approved updates to named issues (use jira), to turn an epic into specs (use jira-brief-intake), or to fix a defect end-to-end (use jira-defect-flow).
- ▌ File To Markdown · eugenelim bundleConvert documents and images to Markdown for AI context layers. Documents (PDF, DOCX, XLSX, PPTX, HTML, EPUB, CSV/TSV, OpenDocument, .eml) go through `scripts/convert.py`, which extracts at a no-ML Tier-0 floor (pure-Python / stdlib parsers) and falls through to Docling (Tier 2) only for .xls and images; images go through a two-pass sliding-window vision pipeline whose tiling and reconciliation are deterministic (`scripts/split_image.py` and `scripts/reconcile.py`). Every output carries a versioned frontmatter contract (provenance + a quality/confidence signal). The agent's job is the per-tile vision read; tile dedup and ordering are handled by the script.
- ▌ Markdown To DOCX · eugenelim bundleFill a branded Word template from a Markdown artifact — turn this Markdown into a Word doc, produce a report, a memo, a statement of work, or a branded .docx. The deterministic script fills the Jinja fill-points a designer placed in the template (front-matter, headings, lists, tables map onto them), so the cover page, styles, headers, and placed logo survive. Use when the user wants a Word document, report, memo, or .docx out of Markdown. Tier-1 on docxtpl (the user installs it; the skill detects it and stops if absent).
- ▌ Markdown To HTML · eugenelim bundleConvert a Markdown file to a self-contained, styled HTML page (sticky header, sidebar nav, syntax-highlighted code, callout boxes, Mermaid diagrams, print-ready). Use when the user asks to render, convert, or export a `.md` file as a shareable HTML document -- not for slides, presentations, or pitch decks. Rendering is deterministic via `marked` + `highlight.js`; the agent only invokes the script.
- ▌ Markdown To PPTX · eugenelim bundleFill a branded PowerPoint template from a Markdown artifact — turn this into slides, build a slide deck or presentation, produce a branded .pptx. The deterministic script inspects the template's layout placeholders and projects your Markdown (front-matter, headings, lists, tables) onto them, so the user's slide master, theme, and placed assets survive. Use when the user wants a PowerPoint, a slide deck, or a presentation out of Markdown. Tier-1 on python-pptx (the user installs it; the skill detects it and stops if absent).
- ▌ Markdown To XLSX · eugenelim bundleFill a branded Excel template from a Markdown artifact — export this table to Excel, fill the .xlsx template, produce a spreadsheet or workbook. The deterministic script writes Markdown content into the named ranges and Excel Tables a designer defined (front-matter into single-cell names, a Markdown table into a Table data region), so the workbook's formatting, formulas, and charts survive. Use when the user wants Excel, a spreadsheet, or an .xlsx workbook out of Markdown. Tier-1 on openpyxl (the user installs it; the skill detects it and stops if absent).
- ▌ Mermaid Renderer · eugenelim bundleExtract ` ```mermaid ` fenced blocks from a Markdown file, render each one to a PNG (or SVG) via the Mermaid CLI (`mmdc`), and write a rewritten Markdown file alongside with each fence replaced by an image reference. Use when the user wants Mermaid diagrams baked into images for downstream tools that don't render Mermaid natively (Confluence, PDF, slides). The agent only invokes the script.
- ▌ Build Outline · eugenelim bundleDecompose a research question into the sub-questions a thorough answer must address. Builds the outline that `/source-map` then populates and `/desk-research` then synthesises against. Grounded in STORM's outline stage (multi-perspective topic decomposition) and PRISMA's PICO framework (Population, Intervention, Comparison, Outcome — the systematic-review decomposition). Produces `<topic-slug>-outline.md` listing each sub-question with a brief rationale. Depth cues — `quickly`, `top three`, `briefly`, `summary only` for the must-answer few; `comprehensively`, `exhaustively`, `in depth`, `extensive` to chase second-order sub-questions.
- ▌ Desk Research · eugenelim bundleEvidence-grounded research with selectable depth and discipline. Use for any look-up, find-out, fact-check, or comprehensive investigation, including prior art and best practice surveys. Carries a mode parameter (quick / standard / applied / deep) with `quick` as default — casual phrasings (`look up`, `find out`, `quick check`) stay quick; academic phrasings (`research with citations`, `evidence-grounded`, `go deep`, `comprehensively`) bias standard or deep; practitioner phrasings (`applied patterns for`, `best practice for`, `prior art on`, `grey literature`) bias applied. Quick mode is inline, ≤5 fetches, no artifact. Standard mode produces `<topic-slug>-survey.md` with GRADE-style confidence per finding from peer-reviewed and primary sources. Applied mode produces `<topic-slug>-survey.md` calibrated for practitioner grey literature with a discipline-aware confidence overlay. Deep mode additionally auto-runs `/devils-advocate`, producing `<topic-slug>-counterpoints.md`.
- ▌ User Flow · eugenelim bundleUse when an approved customer journey needs to become screens, transitions, failure paths, and navigation routes. Produces a complete screen sequence plus one self-contained brief per screen and a whole-flow walk-through. Use `journey-mapping` to understand the journey first, `interaction-design` for behavior within one screen, and `service-blueprint` for backing services. Adoption strategy belongs upstream; appetite and scope belong to `frame-intent`; implementing routes and screens belongs to `frontend-engineering`. Triggers on "turn this account-recovery journey into screens and transitions", "map the error paths across our checkout screens", "create a screen flow and brief for every onboarding screen".
- ▌ Reconcile Iac · eugenelimUse this skill to audit Terraform/OpenTofu drift, reconcile state, run a pre-change preflight, or check an incoming IaC diff for ADR compliance. Triggers on "reconcile my infrastructure", "check for drift", "drift audit", "what drifted", "before I change X check drift", "is my infra in sync", "adr-check", "does this change comply", "check this diff against our ADRs", "compliance check this IaC change". Never autonomously applies. Shares generate-iac's references and reviewers.
- ▌ New Package · eugenelim bundleUse this skill when the user wants to scaffold a new package in the monorepo's `packages/` directory. Triggers on "new package", "create a package called...", "add a library for...". Don't use for new top-level directories (those need an RFC) or for new apps (which go in `apps/`, not `packages/`).
- ▌ AI Adoption Report · eugenelim bundleUse this skill to compare flow-metrics JSON outputs and produce a Markdown comparison report -- "how do our flow metrics now compare to pre-AI?", "within Q4 did AI-tagged tickets behave differently from untagged?", "what does Q4 look like across all teams in the program?". Three modes -- baseline (two windows, one scope), cohort (within-window AI vs control), program (roll up many scopes for one window). Read-only -- consumes flow-metrics JSON files, makes no upstream calls, never invokes flow-metrics / jira / jira-align. Writes only the Markdown report and an optional JSON sidecar.