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

52

Quality

57%

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/superpowers/skills/executing-plans/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

57%

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-organized, concise instruction workflow with clear sequencing and feedback loops, but its verification and review steps are abstract or deferred to the plan rather than concrete, and a recap section adds redundancy. Making checkpoints explicit would lift the weaker dimensions.

Suggestions

Remove the redundant 'Remember' section, since it restates Steps 1-3 and the stop conditions already covered above, tightening conciseness.

Make verification concrete instead of deferred: specify what to run or confirm at each checkpoint (e.g. 'Run the plan's verification commands and confirm tests pass before marking completed') rather than 'Run verifications as specified'.

Replace the abstract 'Review critically - identify any questions or concerns' with a concrete review checklist (e.g. check for missing dependencies, undefined steps, ambiguous verifications).

DimensionReasoningScore

Conciseness

The body is mostly lean bullet-style prose that assumes competence, but the 'Remember' section recapitulates steps already stated in Steps 1-3 and the 'When to Stop' section, and the subagent 'Note' is tangential context, so it is anchor 2 rather than fully efficient.

2 / 3

Actionability

It gives concrete anchors (quoted announcements, named sub-skills, TodoWrite, explicit stop triggers) but 'Review critically - identify any questions or concerns' is abstract and 'Run verifications as specified' defers the detail to the plan, leaving it at anchor 2.

2 / 3

Workflow Clarity

There is a clear three-step sequence with feedback loops ('When to Stop', 'When to Revisit'), but the verification checkpoint is generic and deferred ('verifications as specified') rather than a concrete validate-and-retry step, matching anchor 2.

2 / 3

Progressive Disclosure

Content is well-organized into clearly labeled sections with one-level-deep references to sibling skills and no bundle files or nested references; per the simple-skills note this reaches anchor 3 on organization alone.

3 / 3

Total

9

/

12

Passed

Description

57%

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 an explicit trigger and answers both what and when, but it is written in second person and names a scenario more than multiple concrete actions, with somewhat constructed trigger phrasing. Tightening voice and adding natural action terms would lift the weaker dimensions.

Suggestions

Rewrite in third person and lead with concrete actions, e.g. 'Executes a written implementation plan task-by-task with verification and review checkpoints', to recover the specificity point lost to second-person voice.

Add natural trigger variations users would actually say, e.g. 'Use when executing a plan', 'running an implementation plan', or 'working from a written plan', to broaden trigger-term coverage.

Sharpen distinctiveness by stating what separates this from subagent-driven-development, e.g. 'Use for single-session, non-subagent plan execution with manual review checkpoints'.

DimensionReasoningScore

Specificity

The description names the domain and some specifics ('written implementation plan to execute', 'separate session', 'review checkpoints') which sits at anchor 2, but it uses second-person voice ('you have') which per the rubric guideline reduces the specificity score by 1, landing at 1.

1 / 3

Completeness

It explicitly answers both 'what' (execute a written implementation plan with review checkpoints) and 'when' via an explicit 'Use when...' trigger clause, so it is not capped at 2 and reaches anchor 3.

3 / 3

Trigger Term Quality

'implementation plan' and 'execute' are natural terms a user might say, but 'separate session with review checkpoints' is constructed/technical and common variations like 'running a plan' or 'working from a plan' are missing, matching anchor 2.

2 / 3

Distinctiveness Conflict Risk

The trigger is fairly niche but the skill body references overlapping sibling plan skills (subagent-driven-development, writing-plans), so it could still overlap with similar skills, matching anchor 2.

2 / 3

Total

8

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.