CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

linear-plan

Start work on a Linear ticket by gathering context, planning, creating a branch/worktree, implementing, testing, opening a draft PR, and updating Linear. Use when invoked as `$linear-plan` or when the user asks to start a Linear ticket.

Quality

92%

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

88%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 tight, well-sequenced workflow skill with executable commands at nearly every phase, explicit user-approval checkpoints, and error-recovery loops. The remaining gaps are minor: the fallback PR-creation path and the Phase 8 comment reply lack concrete commands, and the skill is slightly long to score perfectly on structure alone.

Suggestions

Add a concrete command for the Phase 6 fallback (e.g., a `gh pr create --draft --label ...` example) so PR creation is executable in both branches, not just via `$pr-create`.

Show the Phase 8 reply command (e.g., `linear issue comment add <TICKET-ID> --parent <plan-comment-id> ...`) since the plan comment URL/ID is already saved for exactly this purpose.

Consider moving the macOS keychain/sandbox escalation details (~6 lines) into a small reference file to keep the main workflow scannable and bring the body closer to the lean-structure ideal.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence throughout — it spends zero tokens on known concepts and every line carries non-obvious operational detail (keychain/sandbox retry rules, worktree path derivation, commit reference conventions like "Resolves DEVX-696"), matching the "every token earns its place" anchor.

5 / 5

Actionability

Most steps are copy-paste executable (`linear issue view <TICKET-ID> --no-pager`, the full worktree-creation script, `linear issue comment add ... --body-file ...`, `git push -u origin <branch-name>`), but Phase 6's fallback — "otherwise create with ticket-specific labels such as `D-skip-changelog`, `K-*`..." — provides no concrete PR-creation command, and Phase 8's "Reply to the plan thread" omits the reply command, fitting anchor 4's "minor gaps" rather than anchor 5's fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

The eight phases are clearly sequenced with explicit checkpoints ("Present the plans and stop for user selection before implementation", "After plan approval") and genuine feedback loops (retry outside the sandbox on `No keyring entry`; "If a failure is ambiguous or high-risk, pause and report"; fix straightforward failures and commit separately), meeting the top anchor; operations are additive and reversible (draft PR, new branch), so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

The phase headers make navigation easy and nothing that belongs in a separate file is inlined, but the ~97-line body exceeds the under-50-line threshold that would let organization alone justify a 5, and there is no reference structure at all — anchor 4's "good structure; most content appropriately placed; minor organization gaps" is the best fit.

4 / 5

Total

18

/

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.

A strong description that explicitly covers what the skill does (the full ticket lifecycle) and when to use it (named invocation or a direct user request to start a Linear ticket). The only weakness is modest synonym coverage in its trigger terms. No changes needed.

DimensionReasoningScore

Specificity

The description enumerates seven concrete actions — "gathering context, planning, creating a branch/worktree, implementing, testing, opening a draft PR, and updating Linear" — giving comprehensive coverage of the workflow with no gaps, matching the top anchor rather than anchor 4.

5 / 5

Completeness

Both parts are explicit: the "what" is the full seven-action workflow and the "when" is stated verbatim as "Use when invoked as `$linear-plan` or when the user asks to start a Linear ticket", with concrete trigger phrases, meeting the top anchor rather than anchor 4's merely adequate "when".

5 / 5

Trigger Term Quality

It includes natural phrases users would say ("start a Linear ticket", "draft PR", "worktree", "branch") plus the explicit `$linear-plan` trigger, but misses common synonyms such as "Linear issue", "pick up DEVX-…", or "begin this ticket", so it fits anchor 4 rather than the comprehensive-synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — end-to-end Linear ticket workflow — with a distinct invocation trigger, so overlap with generic branch/PR skills is minimal; anchor 5 fits better than anchor 4's "minor overlap risk with closely related skills".

5 / 5

Total

19

/

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

phatblat/dotfiles

Path

.agents/skills/linear-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.