Brummel
4f83305525
Add `specify` as a third co-equal entry path into the dev cycle: it produces an approved spec from already-settled sources (an exhaustive issue, a long in-context design discussion, or a design brainstorm just ratified) with review but no interview. This is the producing half of a deliberate deciding/producing split — `brainstorm` shrinks to optional discovery, `specify` becomes the sole spec-production gate before `planner`, mirroring the RED->GREEN split that keeps tdd/debug honest. What moved: - brainstorm/SKILL.md: stripped of the hard-gate, the acceptance criterion, write-spec, self-review, grounding-check, user-review, and planner-handoff steps; terminal state is now handing a ratified design narrative to specify. Steps renumbered 1-5 (production steps left). - specify/SKILL.md (new): the production core, with a precondition gate (Step 1.5) that bounces to brainstorm the moment the sources do not resolve a load-bearing decision — the same discipline tdd uses. - The grounding-check agent moved brainstorm/agents/ -> specify/agents/ (no-orphan-agents: it lives under its dispatcher), refs repointed. - boss/SKILL.md: Entry-path reflection is now three-way (tdd / specify / brainstorm). specify dispatches autonomously (bounded, no interview) and pauses at its user-review gate; only a fresh brainstorm cycle stays a pre-dispatch bounce-back. - pipeline.md, README, profile-schema, the profile template, and the migration layout updated so every pipeline rendering agrees; specify is a CORE node (not opt-in, unlike tdd) carrying gates: [planner]. Design alternative rejected: parallel sibling skills sharing a docs/spec-production.md (extract-to-doc). Chosen extract-and-chain instead — the shared surface is ~70%, so a shared doc would either become the skill body or drift; chaining keeps one executed home for the gates. Verification (prose repo, no test suite): the spec's internal- consistency grep suite (no two-path drift, no direct brainstorm->planner edge, specify referenced in every rendering, grounding-check single home under specify, specify structural completeness) all green. Orchestrator inspection additionally fixed two dead step-refs the plan under-scoped (a "(Step 4)" lift-validation pointer and a "Skipping Step 7 self-review" red flag, both pointing at steps brainstorm no longer has) and corrected six pre-existing brainstorm->planner renderings in pipeline.md and tdd that predated this cycle. Known follow-ups (non-blocking): the committed spec writes `skills/specify/` in places (typo; skill dirs are repo-top-level) — to be corrected separately. The grounding-check hard-gate was degenerate for this very cycle (this repo has no profile and no test suite); the skip is documented in the spec and the session.
3.5 KiB
3.5 KiB
Migration
This document tracks the migration from AILang's in-tree
~/dev/ailang/skills/ into this plugin.
Each skill is one top-level directory at the repo root,
containing a SKILL.md plus the agent files it dispatches
under agents/. Agents live with their dispatching skill —
this is what makes the "no orphan agents" rule structurally
true rather than only documented.
The boss skill is the migration pilot (landed); the remaining
seven skills follow once the pattern is approved.
Expected layout after migration
~/dev/skills/
├── README.md
├── INSTALL.md
├── install.sh
├── uninstall.sh
├── docs/
├── templates/
├── boss/ (pilot: landed)
│ └── SKILL.md
├── brainstorm/
│ └── SKILL.md
├── specify/
│ ├── SKILL.md
│ └── agents/
│ └── grounding-check.md
├── planner/
│ ├── SKILL.md
│ └── agents/
│ └── plan-recon.md
├── implement/
│ ├── SKILL.md
│ └── agents/
│ ├── implement-orchestrator.md
│ ├── implementer.md
│ ├── spec-reviewer.md
│ ├── quality-reviewer.md
│ └── tester.md
├── audit/
│ ├── SKILL.md
│ └── agents/
│ ├── architect.md
│ └── bencher.md
├── debug/
│ ├── SKILL.md
│ └── agents/
│ └── debugger.md
├── fieldtest/
│ ├── SKILL.md
│ └── agents/
│ └── fieldtester.md
└── docwriter/
├── SKILL.md
└── agents/
└── docwriter.md
boss has no agents — it is itself the dispatcher of the
others, not a dispatcher-of-subagents.
install.sh walks the repo root, treats every top-level
directory that contains a SKILL.md as a skill, and symlinks
it into ~/.claude/skills/<name>; if the skill has an
agents/ subdirectory, that is symlinked into
~/.claude/agents/<name>. Claude Code's flat user-level
discovery still finds everything while the source tree keeps
the structural binding.
Migration checklist per skill
- Strip project-specific paths (
docs/specs,docs/plans,docs/design/INDEX.md,crates/,bench/). - Strip project-specific commands (
cargo build,bench/check.py). - Replace literals with profile-slot references in prose.
- Strip project vocabulary (
AILang,Form A,.ail.json,Boss); use the profile's vocabulary slots. - Strip project-specific contracts (honesty-rule,
feature-acceptance). These belong in the project's own
CLAUDE.md, not the plugin. - Verify the body still reads coherently for a generic project — would it make sense in a Python web service? A TypeScript library?
Migration checklist per agent
- Drop the
ailang-prefix from thename:frontmatter field. The skill path is the disambiguator. - Replace hardcoded standing-reading paths
(
docs/design/INDEX.md, etc.) with a reference to the profile'sstanding_readingsection. - Replace project-specific Iron Law clauses with the universal
discipline constants; project-specific clauses go to the
project's own
CLAUDE.md. - Verify the body still reads coherently for a generic project (see the per-skill checklist above).
- Confirm the
tools:frontmatter list matches the agent template's role-based conventions (read-only review vs implementation vs orchestrator). - Confirm the agent does not have
Agentin its tools list (no nested subagent dispatch).