worktrail-sdd-workflow

Internal SDD workflow executor invoked by /go only. Do not call directly. Executes classified routes A–J: feature planning, implementation (parallel orchestration, PR generation), defect repair, refactoring, spec changes, investigation, and workflow evolution.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/worktrail-sdd-workflow/SKILL.md

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.

The body is an exceptionally actionable, well-sequenced workflow conductor with strong validation checkpoints and clear route navigation. Its main weakness is verbosity from inlined historical incident rationale and a dense Phase 8 that resists progressive disclosure.

Suggestions

Move the datalena PR #2133/#2228 incident narratives into a referenced rationale doc, keeping only the resulting rule inline.

Extract the Phase 8 merge-gate detail (pre-PR gate internals, automerge label enforcement points) into references/merge-gate.md and summarize the rule inline.

Tighten the repeated code-enforcement paragraphs that restate "not agent-narrated" multiple times into a single consolidated statement.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence throughout with no basic-concept padding, but retains verbose historical-incident narration (datalena PR #2133/#2228) and repeated code-enforcement rationale that could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready commands (worktrail-run-record start, worktrail-preflight run, scope-review) with concrete flags, exit codes, and a route→playbook→engine table covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced pipeline (intake → record → execute → validate → PR → merge gate → outcome) with explicit validation checkpoints (pre-PR test gate exit 0, scope-completeness gate, review-thread gate) and fix-and-rerun feedback loops for a PR-producing skill.	5 / 5
Progressive Disclosure	Acts as an overview with clearly signaled one-level references (pipeline-details.md verified present, routes.md, subagent-prompts.md) and a navigation table, though Phase 8's merge-gate detail is heavily inlined and could move to a reference.	4 / 5
	Total	18 / 20 Passed

Description

67%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 highly specific and distinct, clearly delineating an internal executor scoped to /go dispatch. Its weakness is the absence of an explicit trigger/when clause and the reliance on internal jargon over natural phrasing, which caps completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit "Use when /go dispatches a classified route (A–J)…" clause so the "when" is stated, not implied.

Surface a few natural-language trigger phrases (e.g. "feature planning", "defect repair", "refactor", "investigation") earlier in the sentence rather than buried inside the route list.

Consider noting the user-facing entry point ("users say /go fix the bug…") to bridge internal jargon to natural invocation language.

Dimension	Reasoning	Score
Specificity	Enumerates concrete route-level actions (feature planning, implementation/parallel orchestration/PR generation, defect repair, refactoring, spec changes, investigation, workflow evolution), giving comprehensive coverage of what the executor does.	5 / 5
Completeness	The "what" is explicit and detailed, but there is no "Use when..." clause or equivalent trigger guidance — the "when" is only weakly implied via "invoked by /go only," which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	It names domain activities but relies on internal jargon ("routes A–J", "SDD workflow executor") and lacks the natural user-facing phrases or synonyms a caller would say, since activation flows through /go rather than user speech.	3 / 5
Distinctiveness Conflict Risk	"Internal SDD workflow executor invoked by /go only. Do not call directly" carves out a sharply scoped niche with distinct triggers and minimal overlap risk against general skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: behindthedash/worktrail
Path: skills/worktrail-sdd-workflow/SKILL.md
Commit: ca98247

Reviewed: ~4 hours ago

Table of Contents

Discovery Implementation Validation

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.