Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

implement-plan

Execute a reviewed implementation plan step by step with verification and standards review

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/implement-plan/SKILL.md

Quality

Content

41%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 maximally concise generated stub that redirects to an external shared skill, which is a legitimate pattern — but here the redirect target does not exist, leaving the skill an empty shell. Judged on what is written, it contains no actionable steps, no workflow, and no resolvable content, with only its brevity beyond reproach.

Suggestions

Make the skill self-contained: inline the essential execution workflow (or bundle the shared skill's content in references/), since `~/.agents/skills/implement-plan/SKILL.md` does not exist in this environment and the redirect dead-ends.

Add the step-by-step execution sequence with explicit verification checkpoints (e.g. implement step → run tests/lint → fix and re-verify → only then proceed) that the description promises but the body never provides.

If delegation to a shared skill is intentional, verify the path resolves in the target environment and add a fallback instruction for when the shared skill is unavailable.

Dimension	Reasoning	Score
Conciseness	The body is two lines — a generator comment and "Load and follow the shared skill at `~/.agents/skills/implement-plan/SKILL.md`" — with zero padding and no over-explanation. Every token earns its place; it cannot be leaner while performing its redirect function.	5 / 5
Actionability	The single directive is precise in form, but it delivers no task-execution guidance, and the referenced file `~/.agents/skills/implement-plan/SKILL.md` does not exist in this environment, so following the instruction dead-ends. Fits anchor 2's 'high-level hints but missing the specific steps to execute' rather than anchor 3, whose concrete guidance must actually resolve to something usable.	2 / 5
Workflow Clarity	The skill's stated purpose is a multi-step process ("step by step with verification"), yet the body contains no steps, no sequence, and no validation checkpoints — everything is delegated to a missing file. The simple-skill exception doesn't apply since this is not a single-action skill, and the missing verification in a batch code-change workflow matches anchor 1 ('steps missing; no validation').	1 / 5
Progressive Disclosure	Structurally the body is a clean one-level-deep, clearly signaled reference — the right SKILL.md pattern in form. But scored against the actual bundle structure, the sole referenced path is dangling and no references/, scripts/, or assets/ files exist, so navigation leads to no content at all. Anchor 2's 'minimal structure' with unusable references is the closest fit; not 1 because there is no nested or wall-of-text navigation problem.	2 / 5
	Total	10 / 20 Passed

Description

53%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 communicates a clear 'what' and a reasonably distinct niche, but it stops there: no 'when to use' trigger guidance and only moderately specific actions. It sits squarely at the midpoint of the rubric — functional but leaving trigger discovery and capability detail to guesswork.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. "Use when the user asks to implement, execute, or work through a reviewed implementation plan".

Make 'verification' and 'standards review' concrete — state what is checked (e.g. "run tests and lint after each step, then re-review the diff against the plan's acceptance criteria").

Include natural trigger synonyms such as "execute the plan", "follow the plan", and "work through the plan steps" so users' phrasing matches without exact wording.

Dimension	Reasoning	Score
Specificity	Names the domain and actions ("Execute a reviewed implementation plan step by step", "verification", "standards review"), but the actions are generic rather than concrete — 'verification' and 'standards review' don't specify what is actually done. Below anchor 4, which requires several specific actions with only minor gaps.	3 / 5
Completeness	Has a clear 'what' ("Execute a reviewed implementation plan step by step with verification and standards review") but the 'when' is entirely absent — no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"implementation plan" is a relevant natural phrase a user might say, but common variations and synonyms ("execute the plan", "follow the plan", "work through the plan") are missing. Above anchor 2 because the keyword is domain-relevant rather than generic.	3 / 5
Distinctiveness Conflict Risk	"Execute a reviewed implementation plan" carves a mostly distinct niche in a plan-workflow suite, with only minor overlap risk against closely related plan-creation or code-review skills. Not 5 because the absent 'when' guidance leaves the boundary with those neighbors unsharpened.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: phatblat/dotfiles
Path: .claude/skills/implement-plan/SKILL.md
Revision: 4d65cab

Reviewed: 8 hours ago

Discovery Implementation Validation

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.

implement-plan

Table of Contents

Is this your skill?