CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

make-plan

Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-crafted orchestration skill: the workflow is explicitly sequenced with validation checkpoints and feedback loops, and guidance is concrete via contracts, Good/Bad examples, and an exact output template. The only real weaknesses are mild — some redundant restatement across sections and a few abstract directives (subagent deployment, grep checks) that stop short of exact commands.

DimensionReasoningScore

Conciseness

The body is imperative and assumes competence — no space is spent explaining what planning or documentation is. However, "Key Principles" and "Anti-Patterns to Prevent" largely restate directives already given in Phase 0 and the phase checklist (~10 of ~100 lines), which is minor duplication that could be trimmed, placing it at anchor 4 rather than 5.

4 / 5

Actionability

Concrete, executable guidance dominates: a 4-item numbered subagent reporting contract, Good/Bad task-framing examples with exact citations ("Copy the V2 session pattern from docs/examples.ts:45-60"), and a copy-paste presentation template. As an instruction-only skill code absence is not penalized; it falls short of 5 because directives like "deploy 'Documentation Discovery' subagents" and "grep checks" name categories without exact commands or prompts.

4 / 5

Workflow Clarity

The sequence is explicit and ordered ("Phase 0: Documentation Discovery (ALWAYS FIRST)" → implementation phases → "Final Phase: Verification") with validation checkpoints throughout: per-phase verification checklists, grep checks and tests in the final phase, the "Reject and redeploy the subagent" feedback loop, and a scope test for phases. This matches anchor 5's explicit validation with error-recovery loops; no destructive/batch cap applies.

5 / 5

Progressive Disclosure

No bundle files exist, and the ~100-line body is well-sectioned with clear headers, keeping all core process guidance appropriately inline. It matches anchor 4 (good structure, content appropriately placed); not 5 because the under-50-line simple-skill exception does not apply and some sections (the presentation template, the See Also routing rules) could be split into reference files.

4 / 5

Total

17

/

20

Passed

Description

78%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.

A strong description with explicit what-and-when structure, third-person voice, and good natural trigger coverage. Its main weakness is specificity: it summarizes only two of the skill's concrete capabilities, so a user scanning the description gets only a partial picture of what the skill produces.

Suggestions

Add 1-2 more concrete actions to the description (e.g., verifying implementations against documentation, presenting a fixed five-section summary) to raise specificity beyond two named actions.

Include common user synonyms such as "roadmap" or "break this down into steps" in the Use-when clause to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

"Create a detailed, phased implementation plan with documentation discovery" names the domain and two concrete actions but stops there — the plan's actual components (phases, delegation, verification) are absent. It matches anchor 3 (1-2 concrete actions, not comprehensive) rather than 4, which requires several specific actions listed.

3 / 5

Completeness

The first sentence explicitly states what the skill does and the second gives an explicit "Use when" clause with concrete trigger phrases ("plan a feature, task, or multi-step implementation"). This clearly matches anchor 5; it is not 4 because the when-guidance is specific and explicit rather than merely present.

5 / 5

Trigger Term Quality

"Use when asked to plan a feature, task, or multi-step implementation" plus "especially before executing with do" covers natural phrasings users would say. A few natural terms are missing (e.g., "roadmap", "break this down", "design doc"), so it sits at anchor 4 rather than 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"phased implementation plan" plus "especially before executing with do" carves a distinct planning niche tied to a sibling execution skill, with only minor overlap risk against generic planning/design skills. It is not 5 because "plan a task" is broad enough to collide with other planning-type skills.

4 / 5

Total

16

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

thedotmack/claude-mem

Path

plugin/skills/make-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.