一键导入
ctx-implement
Execute a plan step-by-step with verification. Use when you have a plan document and need disciplined, checkpointed implementation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Execute a plan step-by-step with verification. Use when you have a plan document and need disciplined, checkpointed implementation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
EXPERIMENTAL (discardable). Hand a loose intent spec (.context/specs/intent-<slug>.md) off to spec-kit's /speckit-specify with a prose synopsis. Optional and graceful — warns and continues if spec-kit is not installed; the intent spec stands either way. Third step of the experimental chain.
EXPERIMENTAL (discardable). Stress-test a plan through adversarial interview, then write a debated brief to .context/briefs/<TS>-<slug>.md. First step of the experimental spec-kit delegation chain: /ctx-experimental-plan → /ctx-experimental-spec → /ctx-experimental-handoff.
EXPERIMENTAL (discardable). Turn a debated brief into a LOOSE intent spec at .context/specs/intent-<slug>.md — deliberately not pre-shaped into spec-kit's template. Second step of the experimental chain: /ctx-experimental-plan → /ctx-experimental-spec → /ctx-experimental-handoff.
Run a disciplined "dream" triage pass over the gitignored ideas/ folder — classify each idea against the codebase and specs, and emit gated, provenance-bearing disposition proposals into the dreams/ notebook for human review. NEVER writes canonical memory and NEVER acts on a proposal. Use when invoked headlessly by the scheduler (cron `claude -p`) or when the user says "run the dream" / "dream over my ideas". The human reviews via /ctx-serendipity.
The human review "garden walk" over ctx-dream proposals. Reads pending proposals from the dreams/ notebook and walks the human through accept / reject / amend / skip, one at a time, substance-forward. Mechanical dispositions apply instantly; generative ones (merge, promote) are done here by reading the full source. Use when the user says "serendipity round", "review my dreams", "walk the garden", or "what did the dream find?". The dream proposes; serendipity disposes.
Record architectural decision. Use when a trade-off is resolved or a non-obvious design choice is made that future sessions need to know.
| name | ctx-implement |
| description | Execute a plan step-by-step with verification. Use when you have a plan document and need disciplined, checkpointed implementation. |
Take a plan (inline text, file path, or from the conversation) and execute it step-by-step with build/test verification between steps.
/ctx-brainstorm or plan mode produces an approved plan/ctx-brainstorm
first to refine it/ctx-implement
/ctx-implement path/to/plan.md
/ctx-implement (the plan from our discussion above)
Parse the plan into discrete, checkable steps. Each step should be:
Present the step list to the user for confirmation:
Implementation plan (N steps):
- [Step description] - verify: [check]
- [Step description] - verify: [check]
- ...
Ready to start?
For each step:
CGO_ENABLED=0 go build -o /dev/null ./cmd/ctxCGO_ENABLED=0 go test ./...Verify after every individual step before proceeding to the next.
After every 3-5 steps (or after a significant milestone):
After all steps complete:
make check or
CGO_ENABLED=0 go build && go test ./...)| Change type | Verification command |
|---|---|
| Go source code | CGO_ENABLED=0 go build -o /dev/null ./cmd/ctx |
| Test files | CGO_ENABLED=0 go test ./... |
| Templates/embeds | CGO_ENABLED=0 go build -o /dev/null ./cmd/ctx |
| Makefile | Run the new/changed target |
| Skill files | Build (to verify embed) + check live copy matches |
| Docs/Markdown only | None required |
| Shell scripts | bash -n script.sh (syntax check) |
When a step fails verification:
If a step fails repeatedly (3+ attempts), stop and ask the user for guidance rather than thrashing.
Progress updates should be concise:
Step 1/6: Create ctx-next skill directory .......... OK
Step 2/6: Write SKILL.md template .................. OK
Step 3/6: Copy to live skill directory ............. OK
Step 4/6: Build to verify template embeds .......... OK
Step 5/6: Run tests ................................ OK
Step 6/6: Mark task in TASKS.md .................... OK
All 6 steps complete. Build and tests pass.
Step 3/8: Add
checktarget to Makefile Addedcheck: build auditafter theaudittarget. Verify:make check... build OK, audit OK. Result: PASS
"I'll implement the whole plan now" [makes all changes at once without verification] "Done! Everything should work."
(No step-by-step, no verification, no checkpoints: this defeats the purpose of the skill.)
Before starting, verify:
During execution, verify:
After completion, verify: