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

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is dominated by a verbose, triple-repeated owner directive that wastes tokens and dilutes concrete guidance; real commands and validation gates exist but are buried. Referenced detail files are signaled but absent from the bundle, and the inline directive should be split out.

Suggestions

Collapse the OWNER OPERATING DIRECTIVE, Decoded operating principles, and Timeless MUST Rules into a single concise rules list — the threefold restatement is the main source of verbosity (lowest-scoring conciseness dimension).

Verify and ship the referenced bundle files (validation.md, tdd.md, triage-issue.md, review-pr.md, release.md, marketing.md, agent-teams.md, communication.md) or remove the dead links, since progressive_disclosure is penalized for missing referenced paths.

Move the bulk of the directive/preamble into a separate reference file so SKILL.md stays a lean overview with the workflow, command reference, and one-level-deep links front and center.

DimensionReasoningScore

Conciseness

The ~300-line OWNER OPERATING DIRECTIVE restates the same principles three times (verbatim quote, 'Decoded operating principles', then 'Timeless MUST Rules') — heavy padding and reiteration rather than lean instruction, matching the verbose/padded score-1 anchor.

1 / 3

Actionability

Concrete commands exist (gh issue view, npx vitest run tests/adapters/, the ctx_batch_execute clone protocol) but are buried under abstract directive prose ('wear your PO hat', 'be agentic, decide'); guidance is partly executable but incomplete and diluted.

2 / 3

Workflow Clarity

A clear Analyze→Recruit→Dispatch→Ping-pong→Ship sequence and blocking validation gates exist, but the workflow is fragmented and obscured by the overlapping verbose directive blocks, leaving the sequence present but checkpoints harder to follow.

2 / 3

Progressive Disclosure

References are well-signaled and one-level deep (validation.md, tdd.md, triage-issue.md, etc.), but none of the referenced bundle files actually exist in the bundle, and the massive directive that should live in a separate file is inlined — matching 'content that should be separate is inline'.

2 / 3

Total

7

/

12

Passed

Description

100%

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, specific description with concrete actions, natural trigger terms, and an explicit 'Use when' clause that answers both what and when. The only minor risk is the breadth of scope (issues, PRs, releases, AND marketing) packed into one skill, but the niche remains distinct.

DimensionReasoningScore

Specificity

Lists many concrete actions ('triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts... fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches'), matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Clearly states what ('Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task.') AND when via an explicit 'Use when...' clause enumerating triggers, matching the score-3 anchor.

3 / 3

Trigger Term Quality

Triggers are natural phrasings a user would say ('triaging issues', 'reviewing PRs', 'fixing bugs', 'syncing branches', 'writing LinkedIn posts') with good coverage of common variations rather than jargon.

3 / 3

Distinctiveness Conflict Risk

Niche is tightly scoped to context-mode ops with a parallel subagent army and 17 adapters; unlikely to trigger for unrelated skills despite the broad issue/PR/release/marketing scope.

3 / 3

Total

12

/

12

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.