CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

implementation-planner

Converts a PRD or requirements document into a structured, phased implementation plan with individual phase files and granular per-task files written to .context/plans/. Also restructures existing monolithic planning documents into digestible, hierarchical directory structures. Creates a root plan index summarising all phases, a numbered phase file per phase, and a numbered task file per task inside each phase directory. Use when the user asks to create an implementation plan, break down a PRD, convert requirements to tasks, structure project phases, generate a roadmap, plan a project in sprints, organise task breakdown, split a monolithic planning doc, or decompose a spec into phases and tasks.

Quality

91%

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

85%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 highly actionable, well-validated workflow document with excellent progressive disclosure into a real, complete bundle. Its one weakness is redundancy: the same mode-mapping and reference information appears in two or three places, inflating token cost without adding signal.

Suggestions

Collapse 'When to use each mode', 'Trigger phrases', and 'Recognition examples' into a single signal-to-mode table — the three sections overlap heavily and could be merged into roughly one.

Keep either the inline 'See references/…' sections or the final References tables, not both — the same four deep-dive files are linked twice.

Delete the 'Notes' section; its additivity rules are already stated (more precisely) in Step 4's 'MUST NOT modify existing files' guidance.

DimensionReasoningScore

Conciseness

The body is mostly efficient — dense tables, exact commands, no explanations of concepts Claude already knows — but it is noticeably duplicated: three overlapping signal-to-mode sections ('When to use each mode', 'Trigger phrases', 'Recognition examples'), reference links repeated both inline and in the final References tables, and a 'Notes' section restating Step 4's additivity rules. This fits 'mostly efficient but could be tightened' rather than the minor-trimming level 4.

3 / 5

Actionability

Guidance is fully executable throughout: copy-paste script invocations with real arguments ('sh scripts/new-task.sh url-shortener-service 01 01 initialise-npm-package'), exact output directory trees, the P{phase}T{task} identifier format with worked slug examples, and a file-to-schema mapping for validation.

5 / 5

Workflow Clarity

Both modes have clearly sequenced numbered steps with explicit validation checkpoints and feedback loops: 'If any file fails: fix the violation and re-run validate-plan.sh. Repeat until exit 0', Mode 2's create-validate-then-delete-source ordering, a pre-split verification checklist, and the ≥9-phase STOP guardrail that forces user confirmation before any files are created.

5 / 5

Progressive Disclosure

Verified against the actual bundle: every referenced path exists (4 deep-dive references, 7 templates, 3 schemas, 6 scripts), all references are one level deep and clearly signaled with 'When to Use' tables, and the body stays an overview pointing outward rather than inlining the detail.

5 / 5

Total

18

/

20

Passed

Description

96%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: third-person, concrete, and comprehensive on both capabilities and explicit trigger phrases. The only weakness is slight breadth in a couple of triggers ('generate a roadmap') that could collide with generic planning skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Converts a PRD or requirements document into a structured, phased implementation plan', 'Creates a root plan index… a numbered phase file per phase, and a numbered task file per task', 'restructures existing monolithic planning documents' — with a concrete output location (.context/plans/), matching the comprehensive-coverage anchor.

5 / 5

Completeness

It explicitly answers both 'what' (PRD-to-phased-plan conversion and monolithic-doc restructuring, with the artifact breakdown) and 'when' ('Use when the user asks to…') with concrete trigger phrases, exactly matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use when' clause enumerates comprehensive natural phrases with synonyms: 'create an implementation plan', 'break down a PRD', 'convert requirements to tasks', 'generate a roadmap', 'plan a project in sprints', 'organise task breakdown', 'split a monolithic planning doc', 'decompose a spec into phases and tasks'.

5 / 5

Distinctiveness Conflict Risk

The PRD-to-plan and planning-doc-restructuring niche is mostly distinct, but the 'generate a roadmap' trigger is broad and could overlap with general roadmap or project-planning skills — minor overlap risk with closely related skills rather than the clear-niche top anchor.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 16 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

pantheon-org/tekhne

Path

skills/project-mgmt/planning-toolkit/implementation-planner/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.