CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

orch

PRIMARY AGENT ONLY. Load to orchestrate a Linear or GitHub work item from preparation through merge.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/orch/SKILL.md
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 a dense, well-indexed orchestration core: it routes commands to workflows, enumerates every script's intent, and enforces artifact-based validation at each stage, with one-level-deep references that are clearly signaled and verifiable. Its weaknesses are the inlined deployment-specific Project Instructions block, heavy reliance on '--help' and external workflow/schemas files for actual usage detail — several of which are missing from the provided bundle — and prose so compressed that following the rules requires real effort.

Suggestions

Move the 'Project Instructions' block (owner timezone, consumer refresh review, Cargo round cleanup) into a dedicated reference file and link to it, so per-deployment details are not loaded on every skill read.

Ensure every path referenced from the body — workflows/*.md, schemas/*.md, README.md — ships in the skill bundle, or note in the body where sibling-skill paths (../reviewer, ../dev) resolve from, since navigation currently dead-ends for missing targets.

Include one concrete end-to-end example invocation (e.g., a filled 'start' or 'review-pr' call with real arguments) so the common case is executable from the body alone rather than deferring all argument detail to '--help' and workflow files.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence throughout — it never explains concepts Claude already knows, and every line carries rule content. Minor trim opportunities exist: the ~35-line inlined 'Project Instructions' block (owner timezone, consumer refresh review, Cargo cleanup, kendex-internal rules like D027/KEN-3338) is deployment/org-specific content read on every load that could live in a reference file, and the version pin 'Requires kendex 1.20.0 or newer' is time-sensitive detail not placed in a deprecated/old-patterns section. This fits 'Efficient; minor instances... that could be trimmed' rather than the fully-earned level-5 'every token earns its place'.

4 / 5

Actionability

Guidance is concretely executable: a 16-command routing table, a ~40-row scripts table with intents, exact script paths ('.agents/skills/orch/scripts/<script>'), and literal commands such as 'git -C [WT_PATH] rev-parse --verify HEAD' and the 'git -C [WT_PATH] diff --no-renames --name-only [BOUND_HEAD] HEAD -- <path>' rebase check. The gap from level 5 is that many invocations defer their actual arguments to '--help' and to workflow files not present in this bundle, so the body alone is not fully copy-paste ready for the common cases.

4 / 5

Workflow Clarity

The cycle is explicitly sequenced ('Get the issue → dev implements → publication, review and fixes in the order from pr-order --help → required CI and review gate → merge') with strong validation checkpoints and feedback loops: artifact-based acceptance ('A round closes on a validated on-disk artifact plus git/tracker state, never on a return message'), bounded fix rounds with re-review narrowing and caps, review-artifact-check as the sole reviewer completion condition, and post-merge box-ticking only on proving artifacts. It stays at level 4 because the detailed per-step sequences are delegated to workflow files absent from this bundle, and the extreme prose density makes the sequencing rules themselves effortful to follow.

4 / 5

Progressive Disclosure

Structure is genuinely good: an overview body acting as an index, command and script routing tables, and one-level-deep references with markdown links and precise section anchors (references/skill-rules.md, references/gates.md, references/oversee-events.md etc., all present in the bundle listing and confirmed to use clear in-file navigation). The organization gaps that keep it below 5: a large portion of referenced targets (workflows/*.md, schemas/*.md, README.md, and cross-skill ../reviewer, ../dev, ../communication paths) do not exist in the provided bundle, and the inlined 'Project Instructions' block is content that would be more appropriately split into a separate reference file.

4 / 5

Total

16

/

20

Passed

Description

70%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.

The description is concise, in third-person-appropriate imperative voice, and clearly scoped to Linear/GitHub work-item orchestration with an explicit load directive. Its main gaps are the thin enumeration of concrete capabilities (only prepare/merge endpoints, with the fuller stage list relegated to the separate `summary` field) and the absence of an explicit 'Use when...' clause with concrete trigger phrases like 'issue', 'pull request', or 'drive to merge'.

Suggestions

Fold the stage list from the `summary` field into the description itself (e.g., 'orchestrate an issue from preparation through implementation, review, submit and merge') so the description alone conveys the full capability set.

Add an explicit trigger clause with natural user phrasings, e.g., 'Use when the user asks to run, drive, or ship a Linear or GitHub issue or pull request to merge'.

Include the natural nouns users say — 'issue', 'pull request', 'PR' — alongside 'work item' to broaden trigger coverage without adding jargon.

DimensionReasoningScore

Specificity

"Load to orchestrate a Linear or GitHub work item from preparation through merge" names the domain and the pipeline endpoints (prepare, merge) but stops short of enumerating the several concrete stages the skill actually covers (delegate, review, submit, hand off — those appear only in the `summary` field). It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than the level-4 anchor, which requires a list of several specific actions.

3 / 5

Completeness

The 'what' is clear (orchestrate a Linear/GitHub work item from preparation through merge) and 'Load to orchestrate... / PRIMARY AGENT ONLY' functions as explicit trigger guidance answering 'when'. The 'when' could still be more specific (no concrete trigger phrases like 'use when asked to drive an issue to merge'), which is exactly the level-4 anchor; level 5 requires explicit 'Use when...' phrasing with concrete triggers.

4 / 5

Trigger Term Quality

Natural terms users would say are present: "Linear", "GitHub", "work item", "orchestrate", "merge". Common variations a user might actually say — "issue", "pull request", "PR", "review", "ship" — are missing, so it falls at 'Good keyword coverage; a few natural terms missing' rather than the comprehensive level-5 coverage with synonyms.

4 / 5

Distinctiveness Conflict Risk

"Linear or GitHub work item... from preparation through merge" carves a clear orchestration niche and "PRIMARY AGENT ONLY" further disambiguates it from sub-agent skills. There is minor overlap risk with closely related sibling skills (dev, reviewer, github) whose scope touches parts of this pipeline, so it sits at 'mostly distinct' rather than the level-5 'clear niche with distinct triggers; minimal conflict risk'.

4 / 5

Total

15

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 10 missing, 8 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 1 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/orch/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.