executing-plans

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

Quality

61%

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

73%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.

This is a well-structured orchestrator skill: the workflow is explicit, validation-gated, and includes genuine feedback loops for blocked or outdated plans. Its weaknesses are redundancy — repeated stop/remember rules and off-topic platform commentary — rather than any structural problem.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean imperative prose, but the subagent/platform meta-commentary Note, the duplicated "Don't force through blockers - stop and ask" line, and a "Remember" section that restates earlier rules could all be trimmed.	3 / 5
Actionability	Concrete numbered steps, verbatim announcement strings, exact sub-skill names, and explicit stop conditions give mostly executable guidance; only "Review critically - identify any questions or concerns" stays vague.	4 / 5
Workflow Clarity	A clear three-step sequence with explicit validation checkpoints ("Run verifications as specified", "After all tasks complete and verified"), error-recovery feedback loops (stop-and-ask conditions, "Return to Review" triggers), and a closing checklist.	5 / 5
Progressive Disclosure	Sections are well organized and external skill references (using-superpowers, finishing-a-development-branch) are clearly signaled one level deep, but the ~66-line body and the inlined platform-support prose sit above the simple-skill bar and could be split out.	4 / 5
	Total	16 / 20 Passed

Description

48%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 has a clear, explicit trigger and a distinct niche, but it undersells the skill: it names the situation without stating what the skill actually does (load, review, execute, report). Expanding the what-side with the skill's concrete behaviors would lift both specificity and completeness.

Suggestions

State what the skill does, not just when: e.g. "Loads a written plan, reviews it critically for gaps, executes every task with verification checkpoints, and reports when complete. Use when you have an implementation plan to execute in a separate session or when resuming a plan from a prior conversation."

Add natural trigger variations such as "run the plan", "work through the plan", or "implement the plan" so users phrasing it differently still hit the skill.

Surface the review-checkpoint behavior as a concrete action (e.g. "stops and asks for clarification rather than guessing when the plan is unclear") to increase specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ("implementation plan to execute in a separate session with review checkpoints") but the only action offered is the generic "execute"; the skill's actual behaviors (load plan, review critically, execute tasks, report) are absent.	2 / 5
Completeness	The "when" is explicit ("Use when you have a written implementation plan") but the "what" is only weakly implied by "to execute", matching the anchor of a thin what rather than anchor 4's solidly-present what.	3 / 5
Trigger Term Quality	"implementation plan", "execute", and "separate session" are natural terms a user might say, but common variations like "run the plan", "work through the plan", or "implement the plan" are missing.	3 / 5
Distinctiveness Conflict Risk	"written implementation plan... separate session with review checkpoints" carves a distinct execution niche versus plan-writing skills, with only minor overlap risk against sibling plan-execution skills like subagent-driven development.	4 / 5
	Total	12 / 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: 899d1fb

Reviewed: 7 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.