executing-plans

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

Quality

62%

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 ./eval/local/skills/benchmarks/dependency/superpowers/executing-plans/SKILL.md

The canonical home for this skill is executing-plans in obra/superpowers

Quality

Content

67%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 well-structured, actionable process skill with clear sequencing, validation checkpoints, and feedback loops; its main weaknesses are redundant recap content and a tangential subagent note. Tightening the 'Remember' section and trimming the Superpowers pitch would improve token efficiency without losing clarity.

Suggestions

Remove or condense the 'Remember' section, since each bullet duplicates guidance already stated in the process steps and stop/revisit sections.

Trim the subagent/Superpowers note to one line (e.g. 'If subagents are available, prefer superpowers:subagent-driven-development instead.') to cut the tangential padding.

Make the per-platform tool reference a clearly signaled, top-level pointer rather than burying it in a parenthetical inside the Note paragraph.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, but the 'Remember' section restates points already made in the process steps (review critically, follow steps, run verifications, stop when blocked) and the subagent/Superpowers note is a tangential paragraph that could be trimmed.	3 / 5
Actionability	Steps are concrete and executable (read plan, create todos, mark in_progress/completed, invoke the required sub-skill by name), but a few steps defer specifics to the plan ('Follow each step exactly', 'Run verifications as specified') rather than standing alone.	4 / 5
Workflow Clarity	The three-step sequence is explicit with checkpoints (review before starting, run verifications, stop on repeated failure) and feedback loops (return to Step 1, stop and ask), but the actual validation content is delegated to the plan rather than defined here, a minor gap keeping it just below 5.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with one-level-deep, clearly signaled references to sibling skills; no bundle files exist. It sits just over the simple-skill line (~65 lines) and the per-platform reference is tucked into a parenthetical, so it stops short of a clean 5.	4 / 5
	Total	15 / 20 Passed

Description

57%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 answers both what and when with a reasonably specific trigger, but it relies on second-person voice ('you have') and offers only one generic action with limited keyword variation. Rewriting in third person with a broader set of natural trigger phrases would lift the specificity and trigger dimensions.

Suggestions

Rewrite in third-person voice (e.g. 'Executes a written implementation plan...') to avoid the second-person specificity penalty.

Expand the trigger clause with natural synonyms a user might actually say, e.g. 'Use when given a plan to run, follow, or carry out, especially in a separate session with review checkpoints.'

Surface 1-2 more concrete actions (e.g. 'review the plan critically, execute each task, run verifications, report completion') to move specificity toward comprehensive.

Dimension	Reasoning	Score
Specificity	The description names the domain (executing an implementation plan) and mentions 'review checkpoints', but the action 'execute' is generic and the use of second person ('you have') triggers a 1-point specificity penalty per the voice guideline, dropping it from 3 to 2.	2 / 5
Completeness	Both 'what' (execute a written implementation plan in a separate session with review checkpoints) and 'when' ('Use when you have...') are present and fairly explicit, but the trigger is a single condition rather than a comprehensive set of concrete trigger phrases.	4 / 5
Trigger Term Quality	'implementation plan', 'execute', and 'review checkpoints' are relevant natural terms, but common synonyms and variations a user might say (e.g. 'run a plan', 'follow a plan', 'carry out') are missing.	3 / 5
Distinctiveness Conflict Risk	The 'separate session with review checkpoints' framing carves a clear niche distinct from writing-plans, but there is minor overlap risk with the related plan/development-branch skill family referenced in the body.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/superpowers/executing-plans/SKILL.md
Commit: 2ff42ff

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.