CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

executing-plans

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

Quality

52%

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 ./.agents/harness/adapters/antigravity/skills/executing-plans/SKILL.md

The canonical home for this skill is executing-plans in phatblat/dotfiles

SKILL.md
Quality
Evals
Security

Quality

Content

41%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 maximally lean but is a pure redirect: it delegates everything to an external shared-skill path outside the bundle, providing no actionable steps, no workflow, and no overview. Within this bundle the reference cannot be resolved, so the skill has essentially no standalone content.

Suggestions

Include a brief inline overview of the execution workflow (load the plan, execute steps, pause at review checkpoints) so the skill retains value even when the shared file is unavailable.

Reference the shared skill via a path inside the skill's own directory (or vendor it into references/) so the reference resolves within the bundle.

If the delegation pattern is intentional, at minimum summarize what the target skill covers and when to consult it, giving this SKILL.md a navigable structure.

DimensionReasoningScore

Conciseness

The body is two lines — a provenance comment and a single directive — with zero padding and no explanation of things Claude already knows; every token earns its place.

5 / 5

Actionability

"Load and follow the shared skill at `~/.agents/skills/executing-plans/SKILL.md`" is a concrete directive with an exact path, but it provides no steps for the skill's actual task (executing a plan with review checkpoints), leaving only minimal concrete guidance with the executable specifics delegated entirely elsewhere.

2 / 5

Workflow Clarity

No steps or sequence appear anywhere in the body despite the skill's purpose being an inherently multi-step process (plan execution with review checkpoints); there is no step ordering and no validation or checkpoint guidance, matching the "steps missing; no sequence" anchor.

1 / 5

Progressive Disclosure

The body is a bare redirect with no overview or sections, and its sole reference points outside the skill bundle to `~/.agents/skills/executing-plans/SKILL.md` — a path that does not exist in this bundle (no references/, scripts/, or assets/ are present, and the comment's cited `scripts/agent-harnesses.py` is also absent), so the file has no navigable structure of its own; it is not a monolithic wall (ruling out 1), but structure is minimal and the reference leaves the bundle.

2 / 5

Total

10

/

20

Passed

Description

42%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 offers a clear, fairly specific trigger with natural keywords, but it never states what the skill actually does, and its second-person voice further weakens specificity. It reads as half a description: a good 'when' clause missing its 'what' clause.

Suggestions

Add an explicit 'what' clause naming concrete actions, e.g. "Executes a written implementation plan step by step, pausing at review checkpoints for user confirmation. Use when...".

Rewrite in third person to satisfy the rubric's voice requirement ("Executes a plan..." rather than "Use when you have...").

Broaden keyword coverage with natural variations such as "follow the plan", "carry out the plan", or "work through the task list".

DimensionReasoningScore

Specificity

The description names a domain ("written implementation plan", "review checkpoints") but states no actions the skill performs, which fits anchor 2 ("names the domain but actions are minimal or generic"); the second-person phrasing "Use when you have" triggers the rubric's voice penalty, reducing the score by 1 to 2.

1 / 5

Completeness

Only the 'when' is present ("Use when you have a written implementation plan to execute in a separate session with review checkpoints") with no explicit statement of what the skill does, matching anchor 2 ("only 'when' is present without 'what'"); the what is merely implied, and the rubric forbids inferring it.

2 / 5

Trigger Term Quality

"implementation plan", "execute", "separate session", and "review checkpoints" are natural terms a user would say when needing this skill, though common variations like "follow the plan" or "carry out" are missing — good coverage with a few natural terms absent.

4 / 5

Distinctiveness Conflict Risk

The conjunction of "written implementation plan", "execute", "separate session", and "review checkpoints" carves a mostly distinct niche with only minor overlap risk against closely related plan-writing or code-review skills; it is not entirely generic enough for a lower score.

4 / 5

Total

11

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

phatblat/dotfiles

Path

.agents/harness/adapters/antigravity/skills/executing-plans/SKILL.md

Revision

4d65cab

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill