prekuter/dryforge / agent-plugin/skills/go
go
VerifiedCarry out the intent approved in `ready`, as meant, and prove it with checks that actually ran. Comes back to you if the work would change what you approved, keeps the project docs in step, and never merges on its own. Use when the user invokes the `go` skill after `ready`. Requires git.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 28.4 KB |
| references/foundation-format.md | markdown | 5.3 KB |
| references/graph-contract.md | markdown | 4.4 KB |
| references/harness-format.md | markdown | 28.8 KB |
| references/harness-lifecycle.md | markdown | 6.6 KB |
| references/harness-review.md | markdown | 7.3 KB |
| references/implementer-prompt.md | markdown | 5.7 KB |
| references/orchestration.md | markdown | 24.8 KB |
| references/reviewer-prompt.md | markdown | 3.4 KB |
| references/spec-review-prompt.md | markdown | 2.5 KB |
references/spec-review-prompt.md
View on GitHub# spec-review-prompt.md — conditional mid-run spec review
Dispatched only when the orchestrator judges that a **RISKY task with downstream dependents** could
cascade a deviation. Checks the task's diff against the **spec requirement** before merge — a spec
violation caught late costs an undo/redo across dependent tasks. This is *conformance*, not code
quality.
## Independence — what the reviewer is given
To stay independent, the reviewer receives **only** (a) the spec requirement(s) for the task and
(b) the raw diff / task branch — both **passed inline** (the worktree has no `.dryforge/` files;
`.dryforge/` is gitignored). It is **not** given the implementer's summary, `concerns`, or test
claims — re-derive conformance from the diff itself, do not anchor on the author's narrative.
For a declared **no-file-diff task** (state / operational / external — work whose result lives
outside the tree), there is no raw file diff to read: judge conformance from the commit message
plus the captured external evidence passed inline, not from a diff that doesn't exist.
## What to check
Given the spec requirement(s) for the task + the task's diff, in an independent context: does
the implementation **do what the spec says** — behavior, invariants, edge-case rules, API
surface? Judge conformance to the spec, nothing else. For a no-file-diff task the same question
holds against the commit message + captured external evidence rather than a file diff.
## Calibration
Flag a **real spec deviation** — missing behavior, a violated invariant, an edge case the spec
specifies that the code doesn't handle. Do **not** flag style, naming, or quality — that is the
final reviewer's job. spec is "correct"; measure against it.
If the task's spec slice names a testable risk (edge case, invariant, validation) but the task was
classified RISK=NONE and shipped without a test, flag needs-fix — a real risk was sized away.
## Structured return
- `status`: `pass` | `needs-fix`
- on `needs-fix`: the spec requirement violated + what is missing/wrong (specific enough to fix)
## escalate — when the spec itself is the problem
If the **spec** is ambiguous or self-conflicting (not just the implementation), say so — do not
pick an interpretation. The orchestrator escalates to the user; spec is ground truth and only
the user changes it.
You are in a fresh session with no live user conversation — do NOT ask the user directly. Escalate
via your structured return (`status: needs-fix`, naming the spec problem); the orchestrator relays
escalations to the user.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |