Agent skill
implement
Executes implement-stage loop workflow for the next scoped work item through stage-chain orchestration. Use when implement stage enters loop mode.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/implement-grinrus-ai-driven-dev
SKILL.md
Follow feature-dev-aidd:aidd-core and feature-dev-aidd:aidd-loop.
Steps
- Inputs: resolve active
<ticket>/<scope_key>and confirm loop artifacts are present for implement stage. - Stage-chain policy: execute via canonical stage-chain orchestration through stage runtime entrypoint; internal preflight/postflight are orchestration details and not operator commands.
- Manual write/create of
stage.implement.result.jsonis forbidden; stage-result files are produced only by stage-chain postflight.[AIDD_LOOP_POLICY:MANUAL_STAGE_RESULT_FORBIDDEN] - Runtime-path safety: use only runtime commands from this skill contracts. If stdout/stderr contains
can't open file .../skills/.../runtime/..., stop with immediate BLOCKEDruntime_path_missing_or_drift; one runtime-path error is terminal for current run, do not invent alternate filenames, and do not retry guessed commands. - Retry safety: do not rerun the same failing shell command more than once without new evidence/artifacts. For cwd/build mismatches, stop with blocker and handoff instead of looped retries.
- Read order after stage-chain preflight artifacts:
readmap.md-> loop pack -> review pack (if exists) -> rolling context pack; do not perform broad repo scan before these artifacts. - Run subagent
feature-dev-aidd:implementer. - Orchestration: use the existing rolling context pack (do not regenerate it), Fill actions.json (v1) at
aidd/reports/actions/<ticket>/<scope_key>/implement.actions.json, keep action types strictly in{tasklist_ops.set_iteration_done, tasklist_ops.append_progress_log, tasklist_ops.next3_recompute, context_pack_ops.context_pack_update}, and validate schema viapython3 ${CLAUDE_PLUGIN_ROOT}/skills/implement/runtime/implement_run.py. - Canonical stage-chain: internal preflight -> stage runtime -> actions_apply.py/postflight ->
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-flow-state/runtime/stage_result.py; it must produceaidd/reports/loops/<ticket>/<scope_key>/stage.implement.result.json.[AIDD_LOOP_POLICY:CANONICAL_STAGE_RESULT_PATH] - Non-canonical stage-result path under
skills/aidd-loop/runtime/is forbidden (treat as prompt-flow drift).[AIDD_LOOP_POLICY:NON_CANONICAL_STAGE_RESULT_FORBIDDEN] - Output: return stage contract + updated artifacts with explicit handoff/next action.
Command contracts
python3 ${CLAUDE_PLUGIN_ROOT}/skills/implement/runtime/implement_run.py
- When to run: as canonical implement stage runtime before postflight.
- Inputs: ticket, scope/work-item context, and validated actions payload.
- Outputs: stage validation artifacts and status payload for downstream postflight.
- Failure mode: non-zero exit for invalid actions schema or missing stage prerequisites.
- Next action: fix actions/preconditions and rerun runtime validation before postflight.
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-docio/runtime/actions_apply.py
- When to run: mandatory final step in stage-chain postflight after actions validation.
- Inputs:
--actions <path>and optional--apply-log <path>. - Outputs: applied actions, progress/status artifacts, and apply logs.
- Failure mode: DocOps apply failure, boundary guard failure, or status-summary failure.
- Next action: inspect action/apply logs, fix root cause, rerun the stage-chain, and verify canonical stage result exists (
aidd/reports/loops/<ticket>/<scope_key>/stage.implement.result.json).
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-flow-state/runtime/stage_result.py
- When to run: stage-chain postflight stage-result emission only (not operator/manual recovery command).
- Inputs: canonical postflight payload (
ticket,stage,result,scope-key,work-item-key, evidence links). - Outputs: canonical
aidd.stage_result.v1ataidd/reports/loops/<ticket>/<scope_key>/stage.implement.result.json. - Failure mode: non-zero exit on missing required args or invalid stage-result contract fields.
- Next action: fix postflight payload generation and rerun the stage-chain; do not switch to non-canonical loop runtime paths.
Notes
- Implement stage does not run ad-hoc test loops; format-only is allowed and test orchestration is delegated to hook policy.
Additional resources
- Contract schema: CONTRACT.yaml (when: preflight/postflight or actions contract is unclear; why: validate required fields and artifact expectations before rerun).
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?