CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

write-plan

Discuss a feature, draft an implementation plan, and review it through isolated passes

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/write-plan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 tightly written, highly actionable multi-phase workflow with explicit failure paths, validation checkpoints, and safety rails around committing, and it correctly delegates host-specific dispatch mechanics and upstream rationale. Its only weaknesses are minor: a few passages that could be trimmed or offloaded to a reference file.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence (host-dispatch mapping, exact paths, no basic-concept explanations), but minor passages could be trimmed, such as the diff-reflow justification for the no-hard-wrapping rule and the inline commit-convention discovery priority order in Phase 7. This fits anchor 4 ('minor instances of over-explanation') better than the lean anchor 5.

4 / 5

Actionability

Guidance is fully concrete: the exact plan path pattern `plans/YYYY-MM-DD_slug.md`, literal `Dispatch(...)` blocks with agent, model, description, and prompt per pass, an explicit per-host tool mapping, and a concrete fallback commit message `docs(plans): add <slug>`. The Dispatch template's abstraction is explicitly justified by the Host notes, so it satisfies the executable-guidance anchor for an instruction-only skill.

5 / 5

Workflow Clarity

Phases 1–7 are clearly sequenced with explicit checkpoints and feedback loops: the "PLAN TOO AMBIGUOUS TO BREAK DOWN" halt path stops before Phase 7, diligence findings are presented verbatim with a "REQUIRES YOUR JUDGMENT" bucket re-surfaced at the end, and the commit step has explicit validation rails (ask the user first, stage only the plan file, never `--no-verify`). This matches the anchor with explicit validation steps and error-recovery paths.

5 / 5

Progressive Disclosure

The skill is a well-sectioned workflow overview with a clearly signaled, one-level-deep References section pointing to workflow.md and design-decisions.md (no bundle files exist to check), but some detail such as the commit-convention discovery rules is inlined where it could live in a reference. This lands on anchor 4 ('good structure; minor organization gaps') rather than 5.

4 / 5

Total

18

/

20

Passed

Description

58%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 states three concrete, well-chosen actions that make the skill's purpose clear and reasonably distinct, but it entirely lacks a 'when to use' trigger clause and misses natural synonyms like "spec" or "planning". Adding explicit trigger guidance would resolve its main weakness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to plan a feature, turn a spec or idea into an implementation plan, or requests a reviewed step-by-step plan before coding."

Include natural synonyms users would say — "spec", "planning", "design a feature", "break this into steps" — so the description surfaces for those phrasings.

Briefly mention the end artifact (a reviewed, step-by-step plan file) to sharpen both the 'what' and the distinction from general discussion or code-review skills.

DimensionReasoningScore

Specificity

"Discuss a feature", "draft an implementation plan", and "review it through isolated passes" name several concrete actions in the planning domain, but coverage is incomplete (no mention of step breakdown, plan storage, or commit handling), matching the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor 5.

4 / 5

Completeness

The description has a clear 'what' (discuss, draft a plan, review via isolated passes) but no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

"feature" and "implementation plan" are natural terms users would say, but common variations like "spec", "planning", or "design" are absent, fitting the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

The phrase "review it through isolated passes" plus the implementation-plan focus carves a mostly distinct niche, with only minor overlap risk against generic planning or code-review skills, matching anchor 4.

4 / 5

Total

14

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

phatblat/dotfiles

Path

.agents/skills/write-plan/SKILL.md

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.