/skill:kickoff — Interactive Development Start
Purpose: Begin implementation work from a requirements artifact with the operator at the keyboard, following a built-in-first flow: readiness check → plan → implement → review. Does NOT produce audit-grade governed artifacts; for an unattended run, use /skill:execute-prd.
Before the first user update, read simplify and apply its
output guidance to all assistant-written progress, readiness, task and review
summaries, blockers, decisions, and final results. Preserve technical evidence.
When to Use
- Starting standard feature work from an AERS, PRD, story, or spec
- Work is routine enough that governed artifacts aren't required
- You want an operator-supervised readiness → plan → implement → review flow
When NOT to Use
- Work needs audit-grade traceable review artifacts — use a project-specific governed workflow
- You already have a written plan — use
/skill:execute-plan
- You only need planning, not implementation — use
superpowers:writing-plans
Arguments
<path> — path to the requirements artifact (AERS, PRD, spec, story). If not provided, resolve it by the order below.
--skip-readiness — skip the readiness scoring and the ontology halt.
It never skips the ontology revision halt, which is a reopened-decision
guard rather than a scoring step.
Resolution order — first match wins:
- The explicit
<path> argument, if one was supplied.
- The most recently modified
docs/prds/*/AERS.md.
./AERS.md (legacy root location).
- The most recently modified
docs/prds/*/PRD.md.
./PRD.md.
./prompt.md.
If two or more candidates tie within the same tier, do not guess: ask the
operator which is canonical (interactive) or emit a plan-ambiguity finding
and stop (autonomous).
Sibling artifacts — ONTOLOGY.md, UBIQUITOUS_LANGUAGE.md, and PRD.md —
resolve relative to the directory of the resolved requirements file, not the
repo root.
Workflow
Small Change Fast Path
When the ask is a routine, low-risk, convention-bound edit (single-file change, template-aligned config, metadata update):
- Do not reopen routine implementation defaults settled by repo conventions
- Skip phase-by-phase narration
- Report only the decision-driving context, concrete edits, validation, and any real blocker
Standard Path
Load project memory. Check ~/.claude/agent-memory/<repo-slug>/ for a kickoff-context.md file, where <repo-slug> is the current repo's directory name. If it exists, read it — it contains architectural decisions, patterns, and constraints from prior sessions. Surface any relevant entries as "Loaded from project memory: ..." before proceeding. If the directory doesn't exist, skip silently.
Read the artifact. Read the exact artifact or files the user supplied. Prefer reading actual files over guessing content. If no path is given, resolve one:
Resolution order — first match wins:
- The explicit
<path> argument, if one was supplied.
- The most recently modified
docs/prds/*/AERS.md.
./AERS.md (legacy root location).
- The most recently modified
docs/prds/*/PRD.md.
./PRD.md.
./prompt.md.
If two or more candidates tie within the same tier, do not guess: ask the
operator which is canonical (interactive) or emit a plan-ambiguity finding
and stop (autonomous).
Sibling artifacts — ONTOLOGY.md, UBIQUITOUS_LANGUAGE.md, and PRD.md —
resolve relative to the directory of the resolved requirements file, not the
repo root.
Check readiness. Unless --skip-readiness, score the artifact
with the Automated readiness check in
_internal/aers-readiness/SKILL.md. That check is a composite:
structural points plus the ontology contribution produced by
_internal/ontology-readiness/SKILL.md over the sibling
ONTOLOGY.md. Report both the structural verdict and the
Ontology: line — the point values live in those rubrics and are
not restated here:
Readiness: Not ready / Partially ready / Ready
Ontology: Ready / Partial / Absent
Structural score: <n>
Ontology contribution: <0 | +2 | +4>
Composite: <n>
Gaps:
- ...
Both lines are always emitted, even when the ontology contribution
is 0. The structural verdict is the structural score read against the
same bands (see _internal/aers-readiness).
Behaviour by composite verdict:
- Ready → proceed to step 3.
- Partially ready → ask gap questions inline (one at
a time); record as proposed closed decisions; offer
/skill:prd-validate
for a structured interview. Do not auto-invoke it.
- Not ready → halt. Surface the rubric points and
suggest
/skill:prd-validate for the operator to close gaps; do NOT
start coding.
Ontology halt. Halt only when the ontology line is a bare
Ontology: Absent and the structural verdict is
Partially ready or worse. A structural verdict of Ready with a
bare Absent proceeds and logs the missing ontology as a known
risk. Ontology: Absent (trivial domain) never halts.
On a halt, suggest /skill:prd-create to the operator and stop. Do not
auto-invoke /skill:prd-create — it is an interview, the same interaction
boundary as /skill:prd-validate. When the run proceeds on a bare
Absent, tell the operator the ontology is missing and carry it as
a known risk.
Produce only the lightest useful additions: gap report, proposed
closed decisions, contract examples. For the small change fast
path, do not reopen routine defaults already implied by repo
conventions.
Ontology revision halt. The reopened-decision halt extends to
the ontology. It is a reopened-decision guard, not a scoring step, so
it runs regardless of --skip-readiness. An addition entry in the
ONTOLOGY.md Extension Log passes.
A revision — one of exactly five kinds per
_internal/ontology-readiness § Completeness and Extension Rule 4:
changed reference scheme, homonym split, tightened constraint,
reclassified modality, retrofitted temporality — is mode-dependent, and
the mode is read from the mode: header of ONTOLOGY.md: in feature
mode any revision entry in the Extension Log is a halt condition and
halts with an ontology-revision finding; refresh mode follows the
feature rule, so any revision entry halts the same way; in
greenfield mode a revision entry is itself a defect — nothing
existed to revise — and halts the same way; in rewrite mode a
revision entry must be matched by a confirmed closed decision in the
PRD, and is a halt — the same ontology-revision finding — only if it
is not.
Plan. Once the artifact is ready enough to build, use superpowers:writing-plans for implementation planning. Skip for the small change fast path unless the user asks for a plan or the work expands.
Implement. After planning:
- Pre-coding triage & context pruning (
jev-gate): Before starting a multi-file task or loading large repo files into the cloud context window, call triage_coding_task(task_prompt, candidate_files) via the jev-gate MCP server (per _internal/jev-gate, cascading Runtime Tool Args > ./.jev-gate.toml > ~/.config/jev-gate/config.toml). If insufficient_context scores highest, halt immediately and ask the user for clarification. Follow the returned lane (fast_lane vs. deep_lane; < 0.65 confidence or offline defaults to deep_lane), read keep_full files completely, inspect only exported signatures (ast-grep) for keep_signatures_only, and skip drop files.
- Inspect the repo structure and relevant files
- Make precise changes
- Post-generation invariant & shell gating (
jev-gate): Before running non-trivial shell commands, gate via gate_shell_command(command, working_dir) (or bin/jev-shell-hook). After generating a code patch and before slow builds/tests, pass git diff to verify_code_invariants(git_diff) and fix any failed .jev-gate.toml invariant before proceeding.
- Run the repo's existing build, test, lint, or validation commands
- Use background tasks or parallel agents when helpful
- Continue until the change is verified or a real blocker is reached
Review. After implementation, use superpowers:requesting-code-review or /skill:domain-review for a review pass.
Save project memory. After a successful review, append to ~/.claude/agent-memory/<repo-slug>/kickoff-context.md (create if absent):
- Architectural decisions made or confirmed during this session
- Patterns adopted or rejected (with brief rationale)
- Constraints discovered (e.g. "do not use X because Y")
- Anything a future session should know before starting
Use this format:
## Session: <YYYY-MM-DD> — <artifact slug>
- Decision: <what was decided and why>
- Pattern: <what pattern was adopted or rejected>
- Constraint: <what to avoid and why>
Only write entries that aren't already captured in CLAUDE.md or the artifact itself.
Output Contract
Keep updates concise:
- For multi-step work: requirement readiness, plan status, implementation progress, validation results, remaining blockers
- For small changes: decision context, concrete edits, validation, any blocker
- Do not narrate obvious implementation defaults unless they conflict with repo conventions
Rubrics
This skill references:
_internal/jev-gate — for local System-1 pre-coding triage (triage_coding_task), search hygiene (smart_search), diff invariant auditing (verify_code_invariants), and shell gating (gate_shell_command)
_internal/disposition — for governance principles (elevation pass, evidence standard) when applicable
_internal/repo-delivery — for delivery contracts
CRITICAL: Do Not Guess
- Do NOT reopen closed decisions already settled in the artifact, including
settled rows in its ONTOLOGY.md.
- Do NOT skip readiness checks when requirements are still ambiguous.
- Do NOT replace built-in planning/review with a custom prompt workflow.
- Do NOT claim completion without running the repo's existing validation steps.
- Do NOT narrate obvious implementation defaults unless they create a user-visible tradeoff.
Contract
- Inputs: path to a requirements artifact (or the resolution order under
## Arguments when no path is given); optional --skip-readiness. Calls _internal/aers-readiness (composite readiness scoring), _internal/ontology-readiness (the Ontology: verdict line, reached through aers-readiness), /skill:prd-validate and /skill:prd-create (only when the operator opts in interactively), superpowers:writing-plans (planning), superpowers:requesting-code-review or /skill:domain-review (review). Consults _internal/disposition and _internal/repo-delivery.
- Preconditions: in a git repo; artifact exists and is readable; operator is at the keyboard (kickoff is interactive by design — for autonomous flow, use
/skill:execute-prd).
- Outputs: code committed for the requested change; review pass recorded; concise progress updates per the output contract above (decision context, edits, validation, blockers).
- Postconditions: repo's existing validation steps (lint/build/test) have actually run; closed decisions added to the artifact when the operator confirms; no audit-grade governed artefacts (those belong to
/skill:execute-prd).
- Failure modes: readiness
Not ready → halt before coding; blocking ambiguity remaining → halt and ask; any closed decision in the artifact reopened → halt and surface the conflict; a bare Ontology: Absent with a structural verdict of Partially ready or worse → halt and suggest /skill:prd-create to the operator, never auto-invoke /skill:prd-create (a structural Ready with a bare Absent proceeds and logs a known risk, and Absent (trivial domain) never halts); an ontology revision — changed reference scheme, homonym split, tightened constraint, reclassified modality, retrofitted temporality — in feature mode → halt with an ontology-revision finding, and in rewrite mode → the same halt unless the revision entry is matched by a confirmed closed decision in the PRD (mode read from the mode: header of ONTOLOGY.md), while addition entries pass; this revision halt runs even under --skip-readiness.
1---2name: kickoff-23description: 'Use for operator-supervised feature work from a PRD/story/AERS: readiness4 → plan → implement → review, with the operator at the keyboard. Does not produce5 audit-grade governed artifacts; for an unattended run use /execute-prd.'6whenToUse: 'Use for operator-supervised feature work from a PRD/story/AERS: readiness7 → plan → implement → review, with the operator at the keyboard. Does not produce8 audit-grade governed artifacts; for an unattended run use /execute-prd.'9type: flow10disableModelInvocation: false11metadata:12 source: https://skillmd.com/skills/garyld1962/kickoff-213---141516# /skill:kickoff — Interactive Development Start1718**Purpose:** Begin implementation work from a requirements artifact with the operator at the keyboard, following a built-in-first flow: readiness check → plan → implement → review. Does NOT produce audit-grade governed artifacts; for an unattended run, use `/skill:execute-prd`.1920Before the first user update, read [simplify](../simplify/SKILL.md) and apply its21output guidance to all assistant-written progress, readiness, task and review22summaries, blockers, decisions, and final results. Preserve technical evidence.2324## When to Use2526- Starting standard feature work from an AERS, PRD, story, or spec27- Work is routine enough that governed artifacts aren't required28- You want an operator-supervised readiness → plan → implement → review flow2930## When NOT to Use3132- Work needs audit-grade traceable review artifacts — use a project-specific governed workflow33- You already have a written plan — use `/skill:execute-plan`34- You only need planning, not implementation — use `superpowers:writing-plans`3536## Arguments3738- `<path>` — path to the requirements artifact (AERS, PRD, spec, story). If not provided, resolve it by the order below.39- `--skip-readiness` — skip the readiness scoring and the ontology halt.40 It never skips the ontology revision halt, which is a reopened-decision41 guard rather than a scoring step.4243Resolution order — first match wins:44451. The explicit `<path>` argument, if one was supplied.462. The most recently modified `docs/prds/*/AERS.md`.473. `./AERS.md` (legacy root location).484. The most recently modified `docs/prds/*/PRD.md`.495. `./PRD.md`.506. `./prompt.md`.5152If two or more candidates tie within the same tier, do not guess: ask the53operator which is canonical (interactive) or emit a `plan-ambiguity` finding54and stop (autonomous).5556Sibling artifacts — `ONTOLOGY.md`, `UBIQUITOUS_LANGUAGE.md`, and `PRD.md` —57resolve relative to the directory of the resolved requirements file, not the58repo root.5960## Workflow6162### Small Change Fast Path6364When the ask is a routine, low-risk, convention-bound edit (single-file change, template-aligned config, metadata update):65- Do not reopen routine implementation defaults settled by repo conventions66- Skip phase-by-phase narration67- Report only the decision-driving context, concrete edits, validation, and any real blocker6869### Standard Path70710. **Load project memory.** Check `~/.claude/agent-memory/<repo-slug>/` for a `kickoff-context.md` file, where `<repo-slug>` is the current repo's directory name. If it exists, read it — it contains architectural decisions, patterns, and constraints from prior sessions. Surface any relevant entries as "Loaded from project memory: ..." before proceeding. If the directory doesn't exist, skip silently.72731. **Read the artifact.** Read the exact artifact or files the user supplied. Prefer reading actual files over guessing content. If no path is given, resolve one:7475 Resolution order — first match wins:7677 1. The explicit `<path>` argument, if one was supplied.78 2. The most recently modified `docs/prds/*/AERS.md`.79 3. `./AERS.md` (legacy root location).80 4. The most recently modified `docs/prds/*/PRD.md`.81 5. `./PRD.md`.82 6. `./prompt.md`.8384 If two or more candidates tie within the same tier, do not guess: ask the85 operator which is canonical (interactive) or emit a `plan-ambiguity` finding86 and stop (autonomous).8788 Sibling artifacts — `ONTOLOGY.md`, `UBIQUITOUS_LANGUAGE.md`, and `PRD.md` —89 resolve relative to the directory of the resolved requirements file, not the90 repo root.91922. **Check readiness.** Unless `--skip-readiness`, score the artifact93 with the **Automated readiness check** in94 `_internal/aers-readiness/SKILL.md`. That check is a **composite**:95 structural points plus the ontology contribution produced by96 `_internal/ontology-readiness/SKILL.md` over the sibling97 `ONTOLOGY.md`. Report both the structural verdict and the98 `Ontology:` line — the point values live in those rubrics and are99 not restated here:100101 ```102 Readiness: Not ready / Partially ready / Ready103 Ontology: Ready / Partial / Absent104105 Structural score: <n>106 Ontology contribution: <0 | +2 | +4>107 Composite: <n>108109 Gaps:110 - ...111 ```112113 Both lines are always emitted, even when the ontology contribution114 is 0. The structural verdict is the structural score read against the115 same bands (see `_internal/aers-readiness`).116117 Behaviour by composite verdict:118 - **Ready** → proceed to step 3.119 - **Partially ready** → ask gap questions inline (one at120 a time); record as proposed closed decisions; offer `/skill:prd-validate`121 for a structured interview. Do not auto-invoke it.122 - **Not ready** → halt. Surface the rubric points and123 suggest `/skill:prd-validate` for the operator to close gaps; do NOT124 start coding.125126 **Ontology halt.** Halt only when the ontology line is a bare127 `Ontology: Absent` **and** the structural verdict is128 `Partially ready` or worse. A structural verdict of `Ready` with a129 bare `Absent` proceeds and logs the missing ontology as a known130 risk. `Ontology: Absent (trivial domain)` never halts.131132 On a halt, suggest `/skill:prd-create` to the operator and stop. Do not133 auto-invoke `/skill:prd-create` — it is an interview, the same interaction134 boundary as `/skill:prd-validate`. When the run proceeds on a bare135 `Absent`, tell the operator the ontology is missing and carry it as136 a known risk.137138 Produce only the lightest useful additions: gap report, proposed139 closed decisions, contract examples. For the small change fast140 path, do not reopen routine defaults already implied by repo141 conventions.142143 **Ontology revision halt.** The reopened-decision halt extends to144 the ontology. It is a reopened-decision guard, not a scoring step, so145 it runs regardless of `--skip-readiness`. An `addition` entry in the146 `ONTOLOGY.md` Extension Log passes.147148 A **revision** — one of exactly five kinds per149 `_internal/ontology-readiness` § *Completeness and Extension* Rule 4:150 changed reference scheme, homonym split, tightened constraint,151 reclassified modality, retrofitted temporality — is mode-dependent, and152 the mode is read from the `mode:` header of `ONTOLOGY.md`: in `feature`153 mode any `revision` entry in the Extension Log is a halt condition and154 halts with an `ontology-revision` finding; `refresh` mode follows the155 `feature` rule, so any `revision` entry halts the same way; in156 `greenfield` mode a `revision` entry is itself a defect — nothing157 existed to revise — and halts the same way; in `rewrite` mode a158 `revision` entry must be matched by a confirmed closed decision in the159 PRD, and is a halt — the same `ontology-revision` finding — only if it160 is not.1611623. **Plan.** Once the artifact is ready enough to build, use `superpowers:writing-plans` for implementation planning. Skip for the small change fast path unless the user asks for a plan or the work expands.1631644. **Implement.** After planning:165 - **Pre-coding triage & context pruning (`jev-gate`):** Before starting a multi-file task or loading large repo files into the cloud context window, call `triage_coding_task(task_prompt, candidate_files)` via the `jev-gate` MCP server (per `_internal/jev-gate`, cascading `Runtime Tool Args > ./.jev-gate.toml > ~/.config/jev-gate/config.toml`). If `insufficient_context` scores highest, halt immediately and ask the user for clarification. Follow the returned `lane` (`fast_lane` vs. `deep_lane`; `< 0.65` confidence or offline defaults to `deep_lane`), read `keep_full` files completely, inspect only exported signatures (`ast-grep`) for `keep_signatures_only`, and skip `drop` files.166 - Inspect the repo structure and relevant files167 - Make precise changes168 - **Post-generation invariant & shell gating (`jev-gate`):** Before running non-trivial shell commands, gate via `gate_shell_command(command, working_dir)` (or `bin/jev-shell-hook`). After generating a code patch and before slow builds/tests, pass `git diff` to `verify_code_invariants(git_diff)` and fix any failed `.jev-gate.toml` invariant before proceeding.169 - Run the repo's existing build, test, lint, or validation commands170 - Use background tasks or parallel agents when helpful171 - Continue until the change is verified or a real blocker is reached1721735. **Review.** After implementation, use `superpowers:requesting-code-review` or `/skill:domain-review` for a review pass.1741756. **Save project memory.** After a successful review, append to `~/.claude/agent-memory/<repo-slug>/kickoff-context.md` (create if absent):176 - Architectural decisions made or confirmed during this session177 - Patterns adopted or rejected (with brief rationale)178 - Constraints discovered (e.g. "do not use X because Y")179 - Anything a future session should know before starting180181 Use this format:182 ```markdown183 ## Session: <YYYY-MM-DD> — <artifact slug>184 - Decision: <what was decided and why>185 - Pattern: <what pattern was adopted or rejected>186 - Constraint: <what to avoid and why>187 ```188 Only write entries that aren't already captured in CLAUDE.md or the artifact itself.189190## Output Contract191192Keep updates concise:193- For multi-step work: requirement readiness, plan status, implementation progress, validation results, remaining blockers194- For small changes: decision context, concrete edits, validation, any blocker195- Do not narrate obvious implementation defaults unless they conflict with repo conventions196197## Rubrics198199This skill references:200- `_internal/jev-gate` — for local System-1 pre-coding triage (`triage_coding_task`), search hygiene (`smart_search`), diff invariant auditing (`verify_code_invariants`), and shell gating (`gate_shell_command`)201- `_internal/disposition` — for governance principles (elevation pass, evidence standard) when applicable202- `_internal/repo-delivery` — for delivery contracts203204## CRITICAL: Do Not Guess205206- Do NOT reopen closed decisions already settled in the artifact, including `settled` rows in its `ONTOLOGY.md`.207- Do NOT skip readiness checks when requirements are still ambiguous.208- Do NOT replace built-in planning/review with a custom prompt workflow.209- Do NOT claim completion without running the repo's existing validation steps.210- Do NOT narrate obvious implementation defaults unless they create a user-visible tradeoff.211212## Contract213214- **Inputs:** path to a requirements artifact (or the resolution order under `## Arguments` when no path is given); optional `--skip-readiness`. Calls `_internal/aers-readiness` (composite readiness scoring), `_internal/ontology-readiness` (the `Ontology:` verdict line, reached through aers-readiness), `/skill:prd-validate` and `/skill:prd-create` (only when the operator opts in interactively), `superpowers:writing-plans` (planning), `superpowers:requesting-code-review` or `/skill:domain-review` (review). Consults `_internal/disposition` and `_internal/repo-delivery`.215- **Preconditions:** in a git repo; artifact exists and is readable; operator is at the keyboard (kickoff is interactive by design — for autonomous flow, use `/skill:execute-prd`).216- **Outputs:** code committed for the requested change; review pass recorded; concise progress updates per the output contract above (decision context, edits, validation, blockers).217- **Postconditions:** repo's existing validation steps (lint/build/test) have actually run; closed decisions added to the artifact when the operator confirms; no audit-grade governed artefacts (those belong to `/skill:execute-prd`).218- **Failure modes:** readiness `Not ready` → halt before coding; blocking ambiguity remaining → halt and ask; any closed decision in the artifact reopened → halt and surface the conflict; a bare `Ontology: Absent` with a structural verdict of `Partially ready` or worse → halt and suggest `/skill:prd-create` to the operator, never auto-invoke `/skill:prd-create` (a structural `Ready` with a bare `Absent` proceeds and logs a known risk, and `Absent (trivial domain)` never halts); an ontology revision — changed reference scheme, homonym split, tightened constraint, reclassified modality, retrofitted temporality — in `feature` mode → halt with an `ontology-revision` finding, and in `rewrite` mode → the same halt unless the `revision` entry is matched by a confirmed closed decision in the PRD (mode read from the `mode:` header of `ONTOLOGY.md`), while `addition` entries pass; this revision halt runs even under `--skip-readiness`.