lynxlangya/techne/anchor-intake
Claude Code and agent skill by lynxlangya/techne
- community
Checking that the SKILL.md file is still in the repository.
Interrogate a written engineering implementation brief before work starts. Use when a user brings a ticket, PRD, design note, or substantive engineering task brief and wants to begin implementation planning; force every fixed rubric element to be accounted, cite present/weak claims against the brief, surface gaps, solution-as-goal traps, contradictions, and questions, then emit an intent-level plan. Do not use for bare one-line requests, non-engineering artifacts, code diff review, bug fixing, or execution itself.
Install
npx vskill@latest install lynxlangya/techne/anchor-intakeSKILL.md
anchor-intake
Force the skipped move before execution: interrogate the written brief against a fixed engineering implementation rubric, then plan only after gaps and weak assumptions are visible.
Trigger Check
Use this skill when the user provides a substantial written engineering implementation brief: a ticket, PRD, design note, or task brief with enough text to interrogate before work starts.
Do not use it for a bare one-line request, an already precise command, a marketing brief, research proposal, prose draft, code diff review, bug fix, or implementation execution. For unsupported or too-thin artifacts, self-eject in one sentence and write no .techne/plan/<slug> output. If a captured artifact later proves unsupported, use finalize --unscopable --reason ....
Boundary test: can you point to a user-authored written artifact and ask whether it names the engineering goal, users, measurable success threshold, scope, non-goals, inputs, data sources, dependencies, constraints, and acceptance method? If yes, use anchor-intake. If no, eject or ask for the brief first.
Forced Procedure
- Capture the brief. Save the user-authored artifact verbatim. Run:
python3 skills/anchor-intake/scripts/intake_gate.py init --project <root> --plan <slug> --brief-file <path>.
- Read the brief in full. Do not fill the rubric from memory or from the
user's surrounding chat if the value is not in the captured brief.
- Account every fixed rubric element. For each of the ten elements, write
one disposition in .techne/plan/<slug>/intake.json: present with citation and valueItems, present-weak with citation and a dependent question, or gap with a question or visible modelDefault.
- Surface traps and conflicts. Add span-anchored
solution-as-goaland
contradiction findings whenever the brief implies them. Contradictions need two verified spans.
- Ask only dependent questions. Every question must resolve an element or
finding and carry a planDelta. Weak/gap questions must reference the weak span/value or the missing element label.
- Author intent-level steps. Steps are not execution yet. Each step needs an
id, dependsOnAssumptions, dependsOnSteps, verifiableOutcome, and at least one terminal step reachable from a root step.
- Check and repair. Run:
python3 skills/anchor-intake/scripts/intake_gate.py check --project <root> --plan <slug>. Fix structural failures by doing the missing intake work, not by padding JSON.
- Finalize. Run:
python3 skills/anchor-intake/scripts/intake_gate.py finalize --project <root> --plan <slug>. Relay the generated intakeReport.json to the user, especially gaps, weak elements, questions, solution-as-goal findings, contradictions, and warnings.
Script Contract
Artifacts are written under the target project:
Generated .techne/ output belongs to target projects. Do not commit it to this repository.
Minimal intake.json shape:
Use reference.md for the full JSON contract, fixed rubric, STOPLIST/RUBRIC-LABEL set, shape rules, warning semantics, and known weak spots.
Stop Conditions
- Stop before planning if there is no substantial written engineering brief.
- Stop before
finalizeifcheckreports blocking failures. - Stop and use
--unscopable --reasonif the artifact is not an engineering
implementation brief or is too garbled/thin to interrogate honestly.
- Stop before executing the work.
anchor-intakeends at a surfaced report and
intent-level plan; implementation belongs to the next workflow step.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/anchor-intake/SKILL.md
Popularity
- Repository stars
- 105
- Repository forks
- 18
- 7-day trend score
- 23
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/lynxlangya/techne/anchor-intake)