CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

planning

Technical implementation planning and architecture design. Capabilities: feature planning, system architecture, technical evaluation, implementation roadmaps, requirement breakdown, trade-off analysis, codebase analysis, solution design. Actions: plan, architect, design, evaluate, breakdown technical solutions. Keywords: implementation plan, technical design, architecture, system design, roadmap, requirements analysis, trade-offs, technical evaluation, feature planning, solution design, scalability, security, maintainability, sprint planning, task breakdown. Use when: planning new features, designing system architecture, evaluating technical approaches, creating implementation roadmaps, breaking down complex requirements, assessing technical trade-offs.

Quality

84%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-structured orchestration skill: the body stays a lean overview, delegates phase detail to five real one-level-deep reference files, and defines a concrete output structure. The main gaps are minor redundancy (When-to-Use list duplicated from the description, filler closing line) and a few abstract directives that could be made concrete.

Suggestions

Remove the 'When to Use' section (it duplicates the frontmatter description's Use-when clause verbatim) and drop the closing 'Remember:' motivational line — both are pure token cost; cut the 'Quality Standards' bullets that merely restate what output-standards.md already governs.

Make the final review step concrete: replace 'Ensure completeness, clarity, actionability' with a short checklist (e.g., verify each phase file references ./docs/development-rules.md, every requirement has a phase, trade-off sections name a recommended option).

Ground the abstract directives — 'Validate against existing codebase patterns' and 'Research thoroughly when uncertain' — by pointing to the specific phase reference or agent (e.g., 'per codebase-understanding.md') instead of leaving them as free-floating advice.

DimensionReasoningScore

Conciseness

The body is lean overall — YAGNI/KISS/DRY are named without explaining them, and detail is delegated to references. Minor trimmable content keeps it below 5: the 'When to Use' bullets duplicate the frontmatter's Use-when list, the 'Quality Standards' and closing 'Remember:' section add motivational filler ('Plan quality determines implementation success'), and the Workflow Process partially restates the numbered phases.

4 / 5

Actionability

For an orchestration skill the guidance is mostly concrete: per-phase 'Load: references/X.md' directives with explicit skip conditions, a copyable plan directory structure, and clear output rules ('DO NOT implement code', 'Respond with plan file path and summary'). A few directives remain abstract — 'Research thoroughly when uncertain', 'Validate against existing codebase patterns' — without pointing to how or where, which keeps it from 5.

4 / 5

Workflow Clarity

The six-step Workflow Process is clearly sequenced and the five numbered phases include conditional skip logic ('Skip if: Provided with researcher reports'), with a 'Review & Refine' checkpoint at the end. Validation is present but light — the review step says only 'Ensure completeness, clarity, actionability' with no concrete checklist — so it sits at 4 rather than 5. No destructive/batch operations are involved, so the workflow cap does not apply.

4 / 5

Progressive Disclosure

The body is a pure overview: each of the five phases maps to exactly one 'Load: references/<file>.md' reference, all five files exist in the bundle, and inspection confirms they are one level deep with no nested onward skill references (remaining .md mentions are output-plan filenames or external project docs). Content is appropriately split and navigation is easy, matching the anchor-5 structure.

5 / 5

Total

17

/

20

Passed

Description

83%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: it explicitly states both capabilities and use-when triggers with comprehensive keyword coverage. The keyword-stuffed 'Capabilities:/Actions:/Keywords:' structure reads machine-generated, and a few overly broad keywords (security, scalability) slightly raise conflict risk with other technical skills.

DimensionReasoningScore

Specificity

The description lists several specific capability areas — 'feature planning, system architecture, technical evaluation, implementation roadmaps, requirement breakdown, trade-off analysis, codebase analysis, solution design' — giving broad coverage of the planning domain. It falls short of a 5 because the action verbs ('plan, architect, design, evaluate, breakdown technical solutions') are domain-generic rather than concrete operations like 'extract text and tables' or 'fill forms'.

4 / 5

Completeness

It explicitly answers both 'what' (capabilities and actions lists) and 'when' via a concrete 'Use when:' clause — 'planning new features, designing system architecture, evaluating technical approaches, creating implementation roadmaps, breaking down complex requirements, assessing technical trade-offs'. This matches the anchor-5 pattern of the PDF example with concrete trigger phrases.

5 / 5

Trigger Term Quality

The keyword list covers many natural phrases users would say — 'implementation plan', 'roadmap', 'trade-offs', 'sprint planning', 'task breakdown', 'requirements analysis' — with good synonym coverage. A few common natural variations are missing (e.g., 'spec', 'design doc', 'break this down into tickets/tasks'), and no concrete artifact extensions apply here, keeping it at 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The planning/architecture niche is mostly distinct, but very broad keywords like 'security', 'scalability', 'maintainability', and 'architecture' create minor overlap risk with dedicated security-review, code-review, or design-review skills. It is more distinct than anchor 3 ('somewhat specific but could still overlap') but not the clear-niche minimal-conflict case of anchor 5.

4 / 5

Total

17

/

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

samhvw8/dot-claude

Path

skills/planning/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.