CtrlK
BlogDocsLog inGet started
Tessl Logo

implement-spec

Implement a spec from the plans directory

53

Quality

59%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/implement-spec/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The body is a strong, actionable orchestration skill: concrete commands, explicit validation/feedback loops, and clear stopping conditions. Its main weaknesses are minor structural redundancy between the task list and later sections rather than any over-explanation.

DimensionReasoningScore

Conciseness

The body is mostly lean imperative guidance with concrete commands and an example tree; the main trimmable redundancy is that ARCHITECTURE.md and the test/typecheck/lint commands each appear in two sections. This fits 'Efficient; minor instances of over-explanation that could be trimmed' rather than a 3 because it does not explain concepts Claude already knows.

4 / 5

Actionability

It gives concrete, executable guidance: exact commands (`bun run test:run`, `bun run typecheck`, `bun run lint:fix`), the `#src/*` import alias, `*.test.ts` co-location, `loadFixture()` from `fixtures/`, and a directory-tree example. It is not a 5 because there is no complete executable code example, only commands and conventions, leaving minor gaps for a code-producing skill.

4 / 5

Workflow Clarity

The process is clearly sequenced (Your Task 1-9, Autonomous Workflow loop, Stopping Conditions) with explicit validation checkpoints (run tests, typecheck, lint) and a feedback loop (Test -> Fix -> re-run, and stop only when all pass). This matches 'Clear sequence with explicit validation steps; feedback loops for error recovery; checklists'.

5 / 5

Progressive Disclosure

With no bundle files present, the single SKILL.md is well-organized into clear sections (Your Task, Implementation Guidelines, Architecture Patterns, Autonomous Workflow, Stopping Conditions, Commands, Begin) and has no nested references. It is not a 5 because the Architecture Patterns detail and duplicated command listings could be tightened, leaving minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

37%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.

The description is minimal and accurate but undersells the skill: it states only a single action and provides no usage trigger guidance, leaving Claude without explicit cues for when to invoke it. Adding concrete capabilities and a 'Use when...' clause would materially improve it.

Suggestions

Add a 'Use when...' clause with natural trigger phrases (e.g. 'Use when the user asks to implement a spec, plan, or feature from .agents/plans/').

List the concrete actions the skill performs (e.g. 'Reads the spec, plans tasks with TodoWrite, implements the feature, writes tests, and runs typecheck and lint') instead of only 'Implement'.

Include common synonyms and the directory path as trigger terms (spec, specification, plan, .agents/plans/) to improve natural-keyword coverage.

DimensionReasoningScore

Specificity

The phrase "Implement a spec from the plans directory" names the domain (spec implementation) and a single action (implement) but offers no second concrete action, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because no further specific actions are listed.

2 / 5

Completeness

There is a clear "what" (implement a spec) but no "when" / "Use when..." clause, matching the anchor 'Has a clear what but when is missing or only weakly implied'; the missing trigger guidance caps completeness at 3. It is not a 4 because no explicit usage trigger is present.

3 / 5

Trigger Term Quality

Only "spec" functions as a natural user keyword; "plans directory" is project-specific jargon rather than a phrase users would naturally say, fitting 'one or two generic keywords; missing the natural phrases'. It is not a 3 because common synonyms or variations (e.g. specification, plan, feature) are absent.

2 / 5

Distinctiveness Conflict Risk

Tying the trigger to a specific "plans directory" gives it a niche, but the generic verb "Implement" means it could still overlap with other build/implement skills, matching 'Somewhat specific but could still overlap with similar skills'. It is not a 4 because the description is too terse to clearly distinguish it from related implementation skills.

3 / 5

Total

10

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
LibPDF-js/core
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.