Menú
Run ADLC P7 distillation and maintenance workflows in Pi, including lesson-foundry, rejection-mining, skill-mining, scheduled maintenance, skill-rot, model-ratchet, review-calibration, and gate-fuzzing.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| name | adlc-distill |
| description | Run ADLC P7 distillation and maintenance workflows in Pi, including lesson-foundry, rejection-mining, skill-mining, scheduled maintenance, skill-rot, model-ratchet, review-calibration, and gate-fuzzing. |
P7 converts repeated findings into deterministic defenses and keeps cached guidance fresh.
Commands:
adlc lesson-foundry --json
adlc rejection-mining --json
adlc skill-rot .agents/skills plugins/adlc-pi/skills --json
adlc model-ratchet --json
adlc review-calibration --review-cmd "npx adversarial-review --base {base}" --json
adlc gate-fuzzing --json
Scheduled or automated P7 maintenance should invoke this skill and the external $skill-mining workflow when available, with CI cron as the deterministic fallback.
Record a no-op manifest entry when there is nothing to distill so the runner can distinguish "checked and empty" from "skipped."
Whether you just distilled findings or ran the maintenance commands above, finish on
the ledger's own gate — it must exit 0:
adlc lesson-foundry --gate
A non-zero exit names each cluster in .adlc/findings.jsonl that recurs but still
has no banked lesson; each is an undefended cluster. Bank or refine its lesson and
re-run until the gate is green. It is deterministic, keyless, and portable:
.adlc/findings.jsonl is tracked in git (ADR 0014), so the cluster set travels with
the repo and the gate returns the same verdict anywhere it is checked out. It is not
yet wired into the maintenance cron.
Routes agentic development work to the right Agentic Development Lifecycle (ADLC) gate. Use when shaping a spec or ticket, deciding how to fan out work to models, protecting frozen rails during a build, prosecuting a change before merge, or distilling repeated review findings into defenses. Triggers on "shape this spec", "is this ticket ready", "freeze these tests", "prosecute this change", "is this safe to merge", "ADLC", "which gate", "spec-lint", "premortem", "coldstart", "rails-guard", "hollow-test", "behavior-diff".
Prosecute a change before merge (ADLC P5) — prove the tests are load-bearing rather than hollow, make behavior change visible, measure whether review would actually catch a planted defect, and record revision-bound evidence. Use before merging, or on requests like "prosecute this change", "is this safe to merge", "are these tests real", "will review catch anything".
Bootstrap the ADLC runtime in a repository — install the gate toolkit, create the .adlc/ workspace, and wire the CI rails-guard control. Use when adopting the Agentic Development Lifecycle in a repo for the first time, when `adlc --version` fails, when `.adlc/` is missing, or on requests like "set up ADLC here", "install ADLC", "initialize the lifecycle".
Routes agentic development work to the right Agentic Development Lifecycle (ADLC) gate. Use when shaping a spec or ticket, deciding how to fan out work to models, protecting frozen rails during a build, prosecuting a change before merge, or distilling repeated review findings into defenses. Triggers on "shape this spec", "is this ticket ready", "freeze these tests", "prosecute this change", "is this safe to merge", "ADLC", "which gate", "spec-lint", "premortem", "coldstart", "rails-guard", "hollow-test", "behavior-diff".
Refute-charter review discipline for prosecuting a diff against its ticket. Use when asked to act as a prosecutor, reviewer, or to find reasons a change must not merge.
Run ADLC P7 distillation and maintenance workflows in Codex, including lesson-foundry, rejection-mining, skill-mining, scheduled maintenance, skill-rot, model-ratchet, review-calibration, and gate-fuzzing.