jposluns
- 26 skills
- 0 followers
- 6 hours ago last updated
- ▌ Cleanlanguage · jposluns bundleDraft, rewrite, proofread, adapt, edit, review, or quality-assure prose using the Clean Language standard. Use for emails, Teams or LinkedIn messages, executive communications, reports, policies, governance artefacts, technical documentation, incident communications, strategy material, and other finished prose where directness, precision, natural cadence, Oxford English, and removal of generic AI-writing patterns matter. Preserve legal, technical, contractual, quoted, and standards language when alteration could change meaning.
- ▌ Adopt · jposlunsRun-once onboarding for a fork of a project that ships this governance pack. A maintainer's clone carries accumulated operational working-state (audit-trail registers, session handoff, a queue of next actions, per-document review anchors) that is meaningless to a fresh adopter; this skill either resets present machinery-core working-state to clean adopter baselines or, when the configured working-state location is absent, treats it as already clean and creates only the adopter-local state a public versioned consumer requires, settles how the adopter will handle the project's optional external dependencies (their own, or self-contained with in-repo stubs `/adopt` creates or functional in-repo substitutes), strips maintainer-only operational residue, and records the adopter's choices in the project's committed adoption marker so the resume mechanism proceeds in adopter mode without re-asking. It runs ONLY on a confirmed adopter fork (a fork origin), never on the upstream maintainer repository or an upstream mai
- ▌
- ▌
- ▌ Clean Language · jposluns bundleDraft, rewrite, edit, review, or quality-assure prose using the Clean Language standard. Use for emails, Teams or LinkedIn messages, executive communications, reports, policies, governance artefacts, technical documentation, incident communications, strategy material, and other finished prose where directness, precision, natural cadence, Oxford English, and removal of generic AI-writing patterns matter. Preserve legal, technical, contractual, quoted, and standards language when alteration could change meaning.
- ▌
- ▌
- ▌ Reference Audit · jposlunsReference Audit (reference-breadth audit of project content against configured source material)
- ▌
- ▌ Pr Retrospective · jposlunsPer-PR process retrospective, run as a PR's finalizing step before merge. Surfaces what went well, what caused friction, recurring patterns, and proposed improvements. Output is one entry per PR in the improvement-log register; recurring patterns become candidates for pack-rule updates, worker-brief template additions, or new audit gates. Invoke after the PR-scoped validation sweep (`validation-sweep-pr-scoped`; the parent library's `/validate-pr`) returns and before the next-PR planning step.
- ▌ Validation Sweep · jposlunsProject-wide regression sweep run as a follow-up after any issue is identified and corrected, to confirm no sibling issue remains anywhere in the repository. Invoke after fixes that touch multi-surface artefacts, gate inventories, prose claims about repository state, AI-inferred citations, or generated artefacts. Combines the mechanical audit suite with a structured semantic fan-out, and loops until clean.
- ▌ Validate Inference · jposlunsValidates an inferred premise with a concrete observation before an action depends on it. Use when a draft or plan contains "since / because / given X, do Y" where X is a state claim not observed this turn, when about to skip a step because a prior run covered it, when declaring a fix complete because the named occurrence is fixed, or when acting on remembered rather than re-read state. Walks the discipline (name the inference, cost the validation, validate with a tool call, act on the observation) plus its recording step, so a wrong premise is caught by one cheap read instead of cascading into every downstream action built on it.
- ▌ Clarify Before Acting · jposlunsSurfaces ambiguity in one sentence and asks before acting, rather than silently picking. Use when a request supports more than one reasonable interpretation, when an external value the request does not pin down is required, when a project-specific convention must be chosen, or when an unexpected state of the world is encountered.
- ▌ Publication Screening · jposlunsPublication Screening (assess-and-screen protocol for untrusted reference publications)
- ▌ Library Fitness Review · jposlunsTrigger a comprehensive whole-collection library-fitness review with a project-defined catalogue of persona reviewers when a documentation collection (the parent case is a governance/security documentation library) undergoes a major change or reaches its minimum review cadence, quarterly by default unless the adopting project records a different interval. The parent GRC library's major-change triggers are a new domain directory, a new document type, multiple governance rule additions, and a major restructure. Each invocation dispatches a fan-out of independent persona subagents (for example an executive reader, a security practitioner, an auditor, a newcomer) who review every page from a fresh-reader perspective without inheriting maintainer mental models. Catches comprehensibility, usability, logical-structure, standardization, domain quality, auditability, maintainability, and reader-experience gaps that per-change validation sweeps and mechanical audit gates do not detect. Surfaces prioritized recommendati
- ▌
- ▌ Gate Discipline Diagnose · jposlunsDiagnoses a failing CI gate, lint, or audit and fixes the artefact rather than weakening the gate. Use when a gate fails. Use when tempted to bypass a check with --no-verify, blanket suppression, severity-threshold lowering, or exemption-list addition. Use when a pre-commit hook blocks a commit. Use when a required status check on a PR shows red.
- ▌ Artefact Discipline Check · jposlunsRoutes a change through the correct workflow when the change touches a generated artefact or a protected branch. Use before hand-editing a file that is produced by a generator (build outputs, schema dumps, taxonomies, doc portals, scorecards, lockfiles). Use before pushing directly to, force-pushing, or `reset --hard`ing a protected branch (the default branch, release branches, long-lived integration branches). Use when CI flags generated-artefact drift or a protected-branch operation. The workflow redirects to "edit source, run the generator, commit both halves" or "open a PR through the documented merge mechanism", never to "hand-edit the artefact" or "force-push past the check".
- ▌
- ▌
- ▌ Change Tracking Write Entry · jposlunsComposes a CHANGELOG entry (substantive or terse form) for a PR. Use when about to commit, open a PR, or finalize a change. Every PR carries an entry, even if terse; there is no skip path. The entry's required parts (date-and-version header, structured Keep a Changelog sections for substantive entries, file references as markdown links, the "why" not just the "what", verification evidence, phase context) are walked step by step so an entry that would fail the link-coverage gate, the version-monotonicity audit, or the PR-time delta gate is caught at the draft stage rather than at CI.
- ▌
- ▌ High Assurance Verification · jposlunsRun the heavier pre-apply verification harness for a SENSITIVE change, one that is gate-blind on correctness (a fit or semantic property no existence gate can check), delicate at scale (a wide reshape or bulk mapping where a hand-edit is itself a defect risk), and costly to get wrong (a cited or downstream-relied-on artefact). Use before applying such a change, when the maintainer directs absolute-integrity rechecking, or when resuming a sensitive item left open in the register. It composes research fan-out, a mechanical signal pass over the negatives, independent adversarial verifiers from two or more model families (false-negative and false-positive lenses, blind to each other and to the research), a programmatic invariant floor, and a deterministic scripted apply plus re-parse, so apply-correctness does not rest on the orchestrator's in-context precision. It catches the plausible-but-wrong value that survives every existence gate because the gate confirms the value is well-formed, not that it is right.
- ▌ Surface Instruction Concern · jposlunsRuns the stop-consider-confirm protocol when executing a clear instruction as given would be counterproductive. Use when an instruction would destroy or discard committed work, reduce quality or efficiency with no offsetting benefit, contradict a goal the requestor stated, or rest on an apparently stale belief about current state; and when a brief instruction has both a harmful literal reading and a sensible charitable one. Walks the trigger test, the charitable-interpretation and stale-state checks, and the one-round named-options confirmation, calibrated so routine instructions proceed untouched and only material-impact concerns are surfaced, once, concisely.
- ▌ Evidence Grounded Completion · jposlunsVerifies completion claims with evidence before declaring done. Use before stating "done", "complete", "fixed", "shipped", "ready", or any synonym. Use when wrapping up a unit of work and about to summarize to the user. Use when about to acknowledge a user-reported issue with "good catch". Use also before asserting a factual property of an artefact you have not read (a state assertion in research, assessment, planning, or review), not only at completion. Also use before ending a turn on a stated intention ("continuing with X", "next I will do X"), which is a claim about your own next action.
- ▌ Action Before Explanation Of Inaction · jposlunsGrounds explanations of why an external action cannot or will not proceed in a real tool result, not in inference. Use before writing any clause of the form "X is blocked / waiting on / requires / needs / would fail" attached to an external action you have not attempted this turn. Use when about to explain why a PR cannot merge, why CI is waiting, why a deploy is held, why a permission is missing, or why any external system step is not proceeding. The safe action is attempted before the explanation is written; destructive actions are named and asked, not guessed at.