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

89%

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

82%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 strong, highly actionable body: concrete gh commands with verification steps and explicit approval gates for every mutation, and clean sectioning. The main costs are repetition of the 'no implementation details' rule across four places, a slightly redundant Quick Reference table, and a ~250-line monolith whose PR-finalization and refining sections could live in reference files.

Suggestions

State the 'no implementation details in the body' rule once (the blockquote is the strongest placement) and let the 'Don't' list carry a single reminder line instead of restating it in 'Before Creating' and 'Refining an Existing Issue'.

Add one line to the Flow covering what to do when post-create verification shows the wrong title, type, or state (e.g. fix with `gh issue edit` and re-verify), closing the error-recovery loop.

Drop the 'Quick Reference' table (it duplicates commands already shown verbatim) and consider moving 'Finalization' / PR creation into a separate reference file to shrink the always-loaded body.

DimensionReasoningScore

Conciseness

The body is largely lean and imperative with zero time spent explaining concepts Claude already knows, but the no-implementation-details rule is stated four times (the blockquote, 'Before Creating', 'Refining an Existing Issue', and the 'Don't' list), and the opening bold paragraphs plus the 'Quick Reference' table restate content already given. Not 3: the rest of the file is tight, so the padding is a minor trim rather than a pervasive problem; not 5: the repeated rule and duplicate table are over-explanation that could be cut.

4 / 5

Actionability

Every operation has a copy-paste-ready command: full `gh issue create` invocations with example bodies for both leaf and tracker shapes, `gh issue view --json ...` verification, `gh issue edit --body-file`, and a complete `gh pr create --draft` example ending in `Closes #<issue-number>`. The common cases (create, verify, edit, PR) are all covered with concrete approval-gate instructions between them.

5 / 5

Workflow Clarity

The 'Flow' section gives a clear 6-step sequence with explicit checkpoints — 'wait for Josh's approval of that exact text', 'verify what landed' via `gh issue view --json`, and the edit path is view → apply → verify. Not 5: there is no error-recovery loop telling Claude what to do when the post-create/post-edit verification shows the issue landed wrong, which is the missing feedback loop the top anchor asks for; not 3: verification checkpoints are explicit and present everywhere, not merely implicit.

4 / 5

Progressive Disclosure

The single file is well-sectioned with clear headings and no nested references — every cross-reference (CLAUDE.md rules, the `github` skill) is one level deep and clearly signaled. Not 5: at ~250 lines everything is inline; the Quick Reference table, the PR-finalization section, and the refining guidance are candidates for split-out reference files, which keeps it short of the 'content appropriately split' top anchor; not 3: structure and navigation are good, with no buried references.

4 / 5

Total

17

/

20

Passed

Description

92%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.

An excellent description: concrete third-person capabilities, an explicit 'Invoke when' trigger clause with natural user phrasing, and explicit disambiguation from the sibling `issue` and `epic` skills. The only weakness is a slightly thin set of synonyms for the trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Create and refine the GitHub issues and epics', 'draft a standalone issue for one piece of work, or a parent tracker issue (epic) with child issues' — giving comprehensive coverage of the skill's capabilities in third-person voice. Not 4: unlike 'minor gaps in coverage', every capability of the skill (drafting leaf issues, drafting tracker/epic issues, refining) is explicitly named.

5 / 5

Completeness

Clearly answers both questions: what ('Create and refine the GitHub issues and epics that later sessions work...') and when ('Invoke when: planning new work, drafting or editing an issue or epic, or when asked let's plan X'). Both are explicit with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Includes natural phrases users would say — 'planning new work', 'drafting or editing an issue or epic', "when asked 'let's plan X'" — which are strong direct triggers. Not 5: common variations like 'ticket', 'break this work down', 'create an issue', or 'epic planning' are missing, so keyword coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

It draws a sharp boundary against the most likely conflicting skills: 'Counterpart to the `issue` and `epic` skills, which work already-created issues; `planning` authors them.' This is a clear niche with distinct triggers and minimal conflict risk.

5 / 5

Total

19

/

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.