CtrlK
BlogDocsLog inGet started
Tessl Logo

executing-plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints

60

Quality

70%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/executing-plans/SKILL.md

The canonical home for this skill is executing-plans in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 skill body is a well-structured, concise instruction-only workflow with clear sequencing, explicit batch checkpoints, and stop/feedback loops appropriate to batch plan execution. It loses points mainly to redundant recap sections, deferred verification specifics, and a tautological 'When to Use' section.

Suggestions

Remove the 'Remember' section, since every bullet restates guidance already given in the Process and Stop/Ask sections, and merge anything unique into those sections.

Replace the tautological 'When to Use' line with the concrete trigger from the description (e.g. 'Use when executing a written implementation plan in a separate session with review checkpoints.').

Tighten verification guidance with one concrete example of an expected verification step rather than fully deferring to 'as specified' in the plan.

DimensionReasoningScore

Conciseness

The body is mostly lean, assumes Claude's competence, and avoids explaining concepts Claude already knows, but the 'Remember' section recapitulates earlier guidance ('Review plan critically first', 'Stop when blocked, don't guess'), a minor redundancy that keeps it below the fully-lean anchor 5.

4 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: default batch of 'First 3 tasks', TodoWrite in_progress/completed transitions, exact phrases to say ('Ready for feedback.'), and a named sub-skill; verification details are deferred to the plan ('Run verifications as specified'), a minor gap below anchor 5.

4 / 5

Workflow Clarity

Steps 1-5 are clearly sequenced with explicit checkpoints (review before starting, report between batches) and feedback loops (stop-and-ask conditions, revisit Step 1 on plan changes); because the skill itself does not define what verification looks like and defers it to the plan, it sits at anchor 4 rather than 5, and the batch-operation cap is avoided since checkpoints and stop conditions are present.

4 / 5

Progressive Disclosure

No bundle files exist and the skill is well-organized into clearly-headed sections (Overview, Process, Stop/Ask, Revisit, Remember, When to Use) with a single appropriately-signaled one-level sub-skill reference; the tautological 'When to Use' section ('applicable to execute the workflow or actions described in the overview') and the redundant 'Remember' section are minor organization gaps that hold it below anchor 5.

4 / 5

Total

16

/

20

Passed

Description

65%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 clearly answers both what the skill does and when to use it with reasonably natural trigger terms, but it is written in second person voice, which costs it a specificity point under the rubric. It is a solid, low-conflict trigger description with room to expand action coverage and adopt third person.

Suggestions

Rewrite in third person to avoid the second-person penalty, e.g. 'Executes a written implementation plan in a separate session with review checkpoints. Use when a written implementation plan must be executed with checkpointed review.'

List more concrete actions the skill performs (load plan, review critically, execute in batches of 3, report for review between batches) to raise specificity toward a 4-5.

DimensionReasoningScore

Specificity

The description names the domain ('written implementation plan to execute') and 1-2 concrete actions ('execute', 'review checkpoints'), which anchors at 3, but it is written in second person ('Use when you have'), which the rubric penalizes by reducing specificity by 1.

2 / 5

Completeness

Both the 'what' (execute a written implementation plan with review checkpoints) and 'when' ('Use when you have a written implementation plan to execute in a separate session') are present and explicit, but they are blended into a single clause rather than cleanly separated, matching anchor 4 rather than 5.

4 / 5

Trigger Term Quality

Natural terms like 'implementation plan', 'execute', 'review checkpoints', and 'separate session' are phrases a user would plausibly say; minor synonyms like 'run this plan' or 'follow the plan steps' are absent, so it sits below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche (executing a written plan in a separate session with review checkpoints) is fairly distinct with a clear trigger; minor overlap risk remains with general planning or implementation skills, so it does not fully reach the minimal-conflict anchor 5.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.