agent-wave
Orchestrate a wave of parallel agents over the plan/todo queue in a documentation-led repo — asks how many agents, the budget (items/waves, with hours as a…
Assess and add a CONVENTION (a reusable rule, practice, or naming/process standard) to a documentation-led repo — decides FIRST whether it is worth codifying at all, then routes it to the right home (AGENTS.md hard rule, CONVENTIONS.md guidance, GLOSSARY term, or to /new-adr if
$ npx -y skills add EvolveHQ/docflow --skill add-convention --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/add-conventionContext preview
The summary Claude sees to decide when to auto-load this skill.
Assess and add a CONVENTION (a reusable rule, practice, or naming/process standard) to a documentation-led repo — decides FIRST whether it is worth codifying at all, then routes it to the right home (AGENTS.md hard rule, CONVENTIONS.md guidance, GLOSSARY term, or to /new-adr if
name: add-convention description: Assess and add a CONVENTION (a reusable rule, practice, or naming/process standard) to a documentation-led repo — decides FIRST whether it is worth codifying at all, then routes it to the right home (AGENTS.md hard rule, CONVENTIONS.md guidance, GLOSSARY term, or to /new-adr if it is really a one-off decision). Pushes back on premature or duplicate conventions. Use when the user says "add a convention", "make this a rule", "document this practice", "we should always X", or invokes /add-convention. NOT for recording a single architectural/product decision (use /new-adr) and NOT for queueing work (use /new-plan).
Add a convention — but only after assessing whether it should exist and where it belongs. This skill is a gatekeeper and a router, not a stenographer.
1. Confirm the repo is bootstrapped. 2. Read `CONVENTIONS.md` and `AGENTS.md` in full so you can detect overlap with existing rules and judge fit.
Run the shared assessment protocol; the triage (Step 1) and routing (Step 2) questions are asked under it:
**express** — every choice takes its recommended default; only questions with no derivable default (the free-text essentials) are still asked; **guided** — only the questions marked high-impact below, plus the free-text essentials; **full** — every question below. If the repo's `CONVENTIONS.md` records an `Assessment depth:`, pre-select it as the recommended option — the selector always appears; a recorded depth is never applied silently. Otherwise recommend **full** when the request arrived with little or no context and **express** when it is already fully specified. At any question the operator may answer "defaults from here" or "go deeper"; honour the switch immediately.
a one-line reason; wait for each answer.
exposes a structured single-/multi-select question tool, use it and mark the recommended option; otherwise list options A/B/C in plain text and name the recommended one. Use **free text only** where an enumerable set is impossible (e.g. the exact wording).
answer, and never guess scope when invoked with no context.
Questions (skip any the request already answers): 1. **Worth codifying?** — yes (recurring, stable, testable) or no (one-off, duplicate, churn-prone, vague). *Recommended: per the Step 1 triage; this question gates the rest.* *(High-impact — asked in guided.)* 2. **Home** — `AGENTS.md` hard rule / `CONVENTIONS.md` guidance / `GLOSSARY.md` term / actually a decision (hand off to the **new-adr** skill). *Recommended: per the rule's nature (see Step 2).* *(High-impact — asked in guided: the wrong home is churn to move.)* 3. **Enforce in the verify gate?** — yes / no. *Recommended: no, unless the rule is mechanically checkable.* 4. **Wording** — free text (the rule statement itself; asked at every depth).
Apply triage. Recommend **against** adding when:
convention — point to it instead of duplicating.
Recommend **for** adding when it is a recurring decision whose ambiguity causes rework, it is stable, and it can be stated so an agent can follow it without further interpretation. State your recommendation and the reason before doing anything.
Decide the home, and explain the choice:
with the substance in `CONVENTIONS.md`. Use for non-negotiable constraints.
Use for "how we do things" that informs but doesn't gate.
adding the first term enables the glossary layer; place it at the recorded artefact root).
product, or technology choice with alternatives and consequences) → this is an ADR. Stop and offer the **new-adr** skill; do not bury a decision in CONVENTIONS.
If a convention is a triage/process rule (e.g. how incoming work is triaged), prefer `CONVENTIONS.md` with a hard-rule bullet in AGENTS.md only for the parts that are non-negotiable.
Draft the exact wording for its home file. Keep it tight, testable, and in the repo's language. Show the diff. Confirm before writing.
Apply the edit(s). If a convention rises to a hard rule, ensure `AGENTS.md` and `CONVENTIONS.md` stay consistent. Conventional Commit (`docs: ...`); no ADR touched means no `Rationale:` footer is required, but add one if the repo's contract asks for it on convention changes.
Name the rule and propagation performed; list repositories not updated.
<!-- docflow:closing-report -->
End every run, including blocked, failed and stopped runs, with a section headed exactly **Status at a glance**, containing these three labels:
A plugin for ADR-driven, documentation-led projects, working on Claude Code, Claude Cowork, pi, Codex, and OpenCode from the same skill files (see Install).
Repo: EvolveHQ/docflow
Orchestrate a wave of parallel agents over the plan/todo queue in a documentation-led repo — asks how many agents, the budget (items/waves, with hours as a…
Audit a documentation-led repo against its own conventions — contiguous ADR numbering, INDEX sync, plan/ coverage, required sections, status validity,…
Scaffold or retrofit documentation-led conventions (AGENTS.md, CLAUDE.md, CONVENTIONS.md, ADR catalogue, plan/ queue, _agent/ coordination) into a repo. Use…
Decompose a problem, feature, or goal into candidate ADRs and plan items for a documentation-led repo — one decision per ADR, dependency edges, suggested…
Author a new ADR — record a DECISION (what the system must do, or how it is built) in a documentation-led repo. Picks the next contiguous number, chooses the…
Queue a UNIT OF WORK in the plan/todo queue of a documentation-led repo, tracing to an existing ADR — names the owning ADR(s), scope, exit criteria mapped to…