CtrlK
BlogDocsLog inGet started
Tessl Logo

tlc-implement

Implement a work already planned: extracts a checklist, builds it, and proves every check with an independent verifier. Use when the user says "extract a checklist", "build this ticket", "implement this spec", or "tlc-implement". Do NOT use when nobody has decided what to build, or to design the work.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered process skill: clear three-stage workflow with validation checkpoints at every boundary, excellent conditional progressive disclosure to real reference files, and largely actionable guidance. The main cost is verbosity — extensive repeated justifications that could be cut to tighten the body without losing any operative rule.

Suggestions

Conciseness: cut repeated justifications — the 'horizontal cut the pipeline exists to avoid' rationale and the argument for the light default each appear multiple times; state each once and let the rule carry the rest.

Conciseness: trim the multi-sentence philosophical asides (e.g. why a token budget beats a check budget, why Landing rows are written before the code) to one sentence each; the operative rule survives without the essay.

Actionability: tighten abstract directives like 'walk the codebase around what it touches' into a short concrete checklist of what to look for (existing helpers, conventions, adjacent tests).

DimensionReasoningScore

Conciseness

No padding with concepts Claude already knows — every paragraph is project-specific policy — but the body repeatedly justifies the same rationale ('the horizontal cut the whole pipeline exists to avoid' appears three times; the light-profile default is argued twice), so several sections could be tightened without losing information.

3 / 5

Actionability

Guidance is concrete and executable for a process skill: exact artifact paths (`.checks/<feature>.md`), literal thresholds ('accumulate whole slices while the running total stays under 150k tokens'), a concrete diff range (`<feature base>..HEAD`), and counterexamples like 'Proof: npm test'. Minor gaps remain where steps defer to referenced files or stay abstract ('walk the codebase around what it touches').

4 / 5

Workflow Clarity

The EXTRACT → BUILD → VERIFY pipeline is stated up front with a diagram, and each stage carries explicit validation checkpoints: the refuse gate before writing the checklist, handoff 'only on green', 'a red proof is a stop, not a note', renegotiation on a wrong check, and the Verifier dispatched only after the feature's last batch. The Examples and Common failures sections complete the feedback loops.

5 / 5

Progressive Disclosure

All four referenced files exist exactly as one-level-deep paths, each reference is well-signaled in the body with conditional loading instructions ('Under `light` or `standard` skip that file entirely', 'Do not load it during the first pass of Extract'), and the SKILL.md body stays a genuine overview while details live in the references.

5 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete three-stage capability statement, explicit quoted triggers, and a negative boundary that prevents mis-triggering on design or unplanned work. Only minor headroom on synonym coverage of trigger phrases.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full pipeline: 'extracts a checklist, builds it, and proves every check with an independent verifier' — comprehensive and specific for this skill's scope, written in third person ('extracts', 'builds').

5 / 5

Completeness

Both 'what' (extract checklist, build, prove each check with an independent verifier) and 'when' are answered explicitly with quoted trigger phrases, plus an explicit negative boundary ('Do NOT use when nobody has decided what to build, or to design the work').

5 / 5

Trigger Term Quality

Good natural-phrase coverage: 'extract a checklist', 'build this ticket', 'implement this spec', and the skill name itself. A few natural variations users might say are missing (e.g. 'implement this plan', 'work this backlog item'), which keeps it below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Clear niche — implementing already-planned work with an independent-verifier step — with distinct triggers and an explicit 'Do NOT use' clause separating it from design/planning skills, so minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tech-leads-club/agent-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.