executing-plans

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

Quality

43%

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 ./skills/executing-plans/SKILL.md

Quality

Content

67%Scale 1-5

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

This is a solid process-oriented skill that clearly defines a batch execution workflow with review checkpoints. Its main strength is the clear sequencing and explicit stop conditions. Its main weakness is the lack of concrete examples - a sample plan format, example report output, or example TodoWrite usage would significantly improve actionability.

Suggestions

Add a concrete example of what a plan file looks like (format/structure) so Claude knows what to expect when loading one

Include an example of what the Step 3 report should look like with sample verification output

Dimension	Reasoning	Score
Conciseness	Generally efficient and avoids explaining concepts Claude already knows. Minor redundancy in the 'Remember' section which largely restates points already made in the process steps, and the 'When to Use' section adds little value.	4 / 5
Actionability	Provides a clear process structure but lacks concrete examples - no sample plan format, no specific commands, no example of what a report should look like. The guidance is procedural but not executable in the copy-paste sense; it relies on the plan file to provide the actual concrete steps.	3 / 5
Workflow Clarity	Clear 5-step sequence with explicit checkpoints (review before starting, report between batches, stop-and-ask conditions). Has good feedback loops for blockers and when to revisit earlier steps. Minor gap: no explicit validation of the final output beyond deferring to the sub-skill, and the 'Continue' step (Step 4) is somewhat vague about how feedback is incorporated.	4 / 5
Progressive Disclosure	Well-structured with clear sections and appropriate length for a process-oriented skill. References a sub-skill (finishing-a-development-branch) appropriately. No bundle files are provided, but the skill is self-contained enough that this isn't a major issue. Minor gap: could benefit from linking to an example plan format or template.	4 / 5
	Total	15 / 20 Passed

Description

20%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.

This description is critically weak because it only provides a vague 'when' trigger without explaining what the skill actually does. It lacks concrete actions, specific capabilities, and natural trigger terms. The description would be nearly useless for Claude to distinguish this skill from others in a large skill library.

Suggestions

Add a clear 'what' clause describing the concrete actions this skill performs (e.g., 'Executes multi-step implementation plans by breaking them into phases, running code changes, and pausing at defined review checkpoints').

Include natural trigger terms users would say, such as 'execute plan', 'run implementation', 'phased execution', 'checkpoint review', 'continue from where we left off'.

Improve distinctiveness by specifying what kind of implementation plans this handles and how it differs from general task execution or coding skills (e.g., mention session continuity, plan format expectations, or the checkpoint mechanism).

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It doesn't describe what the skill actually does—there are no verbs like 'generates', 'executes', 'creates'. Terms like 'implementation plan' and 'review checkpoints' are abstract concepts, not specific capabilities.	1 / 5
Completeness	The description provides only a 'when' clause ('Use when you have a written implementation plan to execute in a separate session with review checkpoints') but completely lacks a 'what' — it never explains what the skill actually does. Additionally, the 'when' clause uses second person ('you have'), which is atypical. Per the rubric, a missing 'what' caps this low.	2 / 5
Trigger Term Quality	The phrase 'implementation plan' and 'review checkpoints' are somewhat relevant keywords, but they are not natural terms users would typically say. Users might say 'execute the plan', 'run the next phase', or 'continue implementation', none of which are present.	2 / 5
Distinctiveness Conflict Risk	The description is very broad — 'implementation plan to execute' could overlap with any coding, project management, or task execution skill. 'Separate session with review checkpoints' adds some specificity but is still vague enough to conflict with many workflow or planning skills.	2 / 5
	Total	7 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/executing-plans/SKILL.md
Commit: 57c135b

Reviewed: 3 days ago

Table of Contents

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.