CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

planning

Create and refine the GitHub issues and epics that later sessions work — draft a standalone issue for one piece of work, or a parent tracker issue (epic) with child issues. Invoke when: planning new work, drafting or editing an issue or epic, or when asked 'let's plan X'. Counterpart to the `issue` and `epic` skills, which work already-created issues; `planning` authors them. Each issue covers one coherent thing.

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

75%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 highly actionable — every operation has a concrete, executable gh command — and the workflow is clearly sequenced with approval gates and explicit post-create/post-edit verification. Its main weakness is repetition: the no-implementation-detail rule is restated four times and the opening paragraphs duplicate the description, which costs tokens without adding guidance.

Suggestions

State the "no approach, no files, no implementation steps" rule once (the High level, always callout) and let the Don't section reference it instead of repeating it in Before Creating, Refining, and three Don't bullets.

Drop the opening bold paragraphs that restate the frontmatter description, or compress them to a single sentence, keeping only the one-concern rule that isn't already in the description.

Add a brief error-recovery step after the post-create `gh issue view --json` verification (e.g., what to do if the type or state landed wrong) to close the workflow's only validation gap.

DimensionReasoningScore

Conciseness

The core no-implementation-detail rule is stated four times ("High level, always… If you catch yourself typing an implementation detail, delete it", "Do not draft an approach. Do not enumerate files… recipe you baked into the body", the Refining bullets, and three Don't entries), and the opening bold paragraphs restate the frontmatter description — mostly efficient, but noticeably tighten-able (anchor 3), not the minor-trims of anchor 4 or the padded verbosity of anchor 2.

3 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases: `gh issue create` blocks for both leaf and tracker bodies, `gh issue view --json number,title,issueType,state,url` verification, `gh issue edit --body-file`, and `gh pr create --draft` with the `Closes #<issue-number>` line. This matches anchor 5; anchor 4 would leave gaps in the covered cases, which it doesn't.

5 / 5

Workflow Clarity

The Flow section gives a clear 6-step sequence with explicit checkpoints — "Present the full draft… and wait for Josh's approval of that exact text", "Verify the created issue's number, type, and state" backed by a real verification command after both create and edit. It falls short of anchor 5 because there is no error-recovery feedback loop for when verification shows something wrong landed.

4 / 5

Progressive Disclosure

A single-file skill with well-organized sections, decision tables, a Quick Reference, and one clearly signaled external pointer ("see the `github` skill's Sub-Issues section for the command") — good structure with minor gaps (the Quick Reference table duplicates commands already shown, and at ~230 lines some material could be consolidated). This fits anchor 4 rather than anchor 5's fully split, reference-navigated layout.

4 / 5

Total

16

/

20

Passed

Description

87%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 states concrete capabilities in third person, gives an explicit "Invoke when" clause with natural trigger phrases, and actively disambiguates itself from sibling `issue`/`epic` skills. The only weaknesses are a few missing natural synonyms (ticket, story) and slight under-coverage of what the body actually does (PR creation, session tracking).

DimensionReasoningScore

Specificity

Lists several concrete actions — "Create and refine the GitHub issues and epics", "draft a standalone issue for one piece of work", "a parent tracker issue (epic) with child issues" — but omits capabilities the body covers (PR creation, session tracking), so it matches anchor 4 (several specific actions, minor gaps) rather than 5 (comprehensive).

4 / 5

Completeness

Explicitly answers both: the "what" ("Create and refine the GitHub issues and epics… draft a standalone issue… or a parent tracker issue (epic) with child issues") and the "when" with concrete trigger phrases ("Invoke when: planning new work, drafting or editing an issue or epic, or when asked 'let's plan X'"). It is not 4 because the "when" clause is already explicit and specific, matching the anchor-5 example's structure.

5 / 5

Trigger Term Quality

Natural trigger phrases are present — "planning new work", "drafting or editing an issue or epic", "when asked 'let's plan X'" — giving good keyword coverage, but common synonyms like "ticket", "story", or "break down work" are missing, so it fits anchor 4 rather than comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The sentence "Counterpart to the `issue` and `epic` skills, which work already-created issues; `planning` authors them" draws a clear author-vs-work boundary with distinct triggers, giving a clear niche with minimal conflict risk (anchor 5) rather than the minor-overlap anchor 4.

5 / 5

Total

18

/

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

joshmanders/dotfiles

Path

claude/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.