CtrlK
BlogDocsLog inGet started
Tessl Logo

context-mode-ops

Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches.

58

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/context-mode-ops/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%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 has genuine operational structure — blocking gates, a workflow table, validation checklists, and real commands — but it is undermined by severe triple-redundancy of the operating directive, inlined content that belongs in separate files, and a web of references that resolve to nothing. Tightening the philosophy to a single statement and shipping the referenced files would lift every dimension.

Suggestions

Collapse the three redundant statements of the operating directive (verbatim quote, Decoded principles, MUST Rules) into one concise section; the repetition alone accounts for most of the verbosity.

Create the referenced bundle files (validation.md, tdd.md, agent-teams.md, triage-issue.md, review-pr.md, release.md, marketing.md, communication.md) or inline their essential steps so the workflow links actually resolve.

Move the verbatim owner monologue into a separate references/ file and keep SKILL.md as a lean overview pointing to it, restoring real progressive disclosure.

DimensionReasoningScore

Conciseness

The same directive is expressed three times — verbatim owner quote (lines 28-75), 'Decoded operating principles' (79-153), and 'Timeless MUST Rules' (157-247) — and it lectures on concepts Claude already knows ('LLMs lie cheaply', 'LLMs are wide open to hallucination'), making it noticeably verbose and padded.

2 / 5

Actionability

Concrete executable commands are present ('gh pr merge --squash', 'git log -S', 'npx vitest run tests/adapters/', 'npm run typecheck', 'npx skills add ...'), but the bulk is abstract directive prose and the actual per-workflow steps are deferred to reference files that do not exist in the bundle.

3 / 5

Workflow Clarity

A clear high-level sequence (Analyze → Recruit → Dispatch → Ping-pong → Ship) and explicit blocking validation gates (Claim Verification, TDD-First, Grill-Me) with feedback loops exist, but the detailed steps for each workflow point only to missing files (triage-issue.md, review-pr.md, release.md), leaving real gaps.

3 / 5

Progressive Disclosure

References are signaled one-level-deep via markdown links, but none of the referenced files (validation.md, tdd.md, agent-teams.md, triage-issue.md, review-pr.md, release.md, marketing.md, communication.md) exist in the bundle, and the 47-line verbatim owner directive is inlined when it clearly belongs in its own file.

2 / 5

Total

10

/

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, well-structured description that clearly states capability and trigger conditions with concrete, natural-language keywords. Only slightly broad on the distinctiveness axis where generic GitHub-ops triggers could collide with sibling skills.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' ('Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army') and 'when' ('Use when triaging issues, reviewing PRs...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

The 'Use when' clause packs in natural phrases a user would actually say ('fixing bugs', 'reviewing PRs', 'releasing versions', 'writing LinkedIn posts', 'syncing branches') plus synonyms across the issue/PR/release/marketing domain.

5 / 5

Distinctiveness Conflict Risk

The 'context-mode' scoping plus 'parallel subagent army' and '10-20 dynamic agents' carve a clear niche, but generic triggers like 'reviewing PRs' and 'fixing bugs' carry minor overlap risk with general code-review/git-ops skills.

4 / 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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 15 missing

Warning

Total

15

/

16

Passed

Repository
mksglu/context-mode
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.