Files
d29cf651c7 fix(skills): declare activation triggers in descriptions and normalize version metadata (#2618)
* fix(skills): move version into metadata and normalize to semver

29 skills declared `version` at the top level of their frontmatter. The
schema reads it from `metadata`, so tooling that follows the schema either
misses it or has to special-case the top level.

Three motion skills also declared `version: 1.0`, which is not a valid
semantic version; normalized to `1.0.0`.

No behavioral change — frontmatter metadata only.

* fix(skills): state activation triggers in skill descriptions

148 skills described what they cover but never named the situation that
should trigger them. Since the description is what Claude matches against
to decide whether to load a skill, a description without a trigger makes
activation guesswork — the skill is either missed or loaded at the wrong
time.

Added a "Use when ..." clause to each, derived from the skill's own body
(most already stated the trigger under "## When to Use" or in the opening
line; that intent is now reflected in the frontmatter where it is actually
read from).

Descriptions were only appended to; no existing wording was removed.

* fix(skills): sync activation triggers into the Codex skill mirror

10 of the skills whose descriptions changed are also mirrored under
`.agents/skills/`, where the description was previously a verbatim copy.
Left alone, the two surfaces would disagree about when the skill applies.

Only the description line is synced; the Codex copies keep their reduced
frontmatter, since that validator accepts only name, description,
metadata, license, and allowed-tools.

* fix(skills): correct three activation clauses from review

- autonomous-loops: the clause pulled new loop work into a skill that its
  own body marks as a compatibility shim retained for one release. It now
  points at the canonical continuous-agent-loop instead.
- continuous-learning: the description carried the v1 routing directive
  twice; collapsed to one.
- homelab-pihole-dns: the clause fired on any broken home DNS. Narrowed to
  tasks that actually involve Pi-hole.

* chore: retain current main lockfile

---------

Co-authored-by: Çağrı Solakoğlu <cagri.solakoglu@vtcenerji.com>
Co-authored-by: haelyra <49814733+haelyra@users.noreply.github.com>
2026-08-11 23:58:14 -04:00

2.4 KiB

name, description, metadata
name description metadata
orch-build-mvp Orchestrate bootstrapping a working MVP from a design or spec document — ingest the doc, plan thin vertical slices, scaffold the first end-to-end slice, then TDD-implement, review, and gated commit. Use to turn an SDD/PRD into a running starting point. Use when a design or spec document must become a running MVP through planned vertical slices.
origin
ECC

orch-build-mvp

Actor · action · target: orch · build · mvp. Thin wrapper over the shared engine in orch-pipeline.

When to Use

  • The user has a design / spec document (SDD, PRD, system_design) and wants a working vertical slice bootstrapped from it.
  • Takes a doc path as its argument, e.g. civicpulse/docs/SDD-v0.6.md.

Operation settings

  • Default size floor: large — this is the full pipeline including Scaffold.
  • Phase mask: 0 (read the spec) → 1 → 2 (heavy) → 3 (scaffold) → 4 → 5 → 6.
  • First move (phase 0 → 2): read the doc; extract scope, locked decisions, and the feature list; order it into thin vertical slices (one end-to-end path first, not all-models-then-all-views). Phase 3 stands up that first slice.

How It Works

  1. Run the orch-pipeline engine with the settings above.
  2. Reuse the existing GAN harness instead of hand-rolling an iterate loop:
    • Translate the SDD into gan-harness/spec.md + gan-harness/eval-rubric.md (this stands in for what gan-planner would generate — you already have the spec).
    • Drive the build with /gan-build "<one-line brief>" --skip-planner (defaults: --max-iterations 15, --pass-threshold 7.0, --eval-mode playwright; use --eval-mode code-only for non-UI slices).
    • That command runs the gan-generatorgan-evaluator loop and writes gan-harness/feedback/feedback-NNN.md until the score passes or plateaus.
  3. Stop at Gate 1 (slice plan) and Gate 2 (pre-commit). Commit the scaffold and each slice as separate feat: commits.
  4. Add security-reviewer for any slice touching a security trigger.

Example

orch-build-mvp: civicpulse/docs/SDD-v0.6.md
→ read SDD → slice list (vertical) → scaffold slice 1  [GATE 1: approve]
→ /gan-build --skip-planner (generator → evaluator loop) scores vs spec → review
→ commit feat:  [GATE 2: confirm] → next slice