CtrlK
BlogDocsLog inGet started
Tessl Logo

fast-feature

Use when driving a single already-specced ticket through devflow in one session — a quick ambiguity-only brainstorm, then spec, plan, and lock-tests back-to-back, spawning a new session only for the execute phase. Also the per-ticket driver that orchestrate-epic invokes.

66

Quality

83%

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

73%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 well-engineered orchestration skill: the step sequence is unambiguous, validation gates (branch confirmation, Phase 1.8 approval, STOP conditions) are explicit, and every override of a sibling skill's behavior is stated with the exact flag to use. The main cost is redundancy — Common Mistakes, Red flags, and Important restate the same three rules, inflating tokens without adding guidance.

Suggestions

Merge "Common Mistakes" and "Red flags" into a single section: their rows cover the same three rules (suppress intermediate handoffs, skip brainstorm on specced tickets, trust the brief), and each duplicate row costs tokens on every load.

Consolidate the "Important" section into the merged mistakes section, keeping only the two rules not already stated elsewhere (never write production code; always end Step 0 on the feature branch or STOP).

State the --no-handoff override mechanism once in a short note before Step 3 instead of fully re-explaining it in both Step 3 and Step 4 — Step 4 can then just say "override the terminal handoff as in Step 3".

DimensionReasoningScore

Conciseness

The body is mostly efficient, but three overlapping closing sections ("Common Mistakes", "Red flags", "Important") each restate the same rules about suppressing intermediate handoffs, honoring Phase 1.8, and staying on the feature branch, and Steps 3 and 4 repeat the OVERRIDE explanation. This fits anchor 3 ("could be tightened") better than anchor 4, where over-explanation would be only minor.

3 / 5

Actionability

Guidance is mostly executable: a concrete bash worktree block with a fallback for an existing branch, an explicit ticket-key regex, exact override flags ("--no-handoff"), and the exact spawn command `devflow:phase-handoff --phase lock-tests --next-phase impl`. Minor gaps keep it at anchor 4 rather than 5 — placeholders like `slug="<short-kebab-summary>"` and `repo_root` are not copy-paste ready.

4 / 5

Workflow Clarity

Steps 0-6 with a mermaid flowchart give a clear sequence, and validation is explicit: "Confirm: `git branch --show-current` == `$branch`. If not, STOP", Phase 1.5 "verify each fails for the right reason", the Phase 1.8 user-approval gate ("Do NOT proceed past Phase 1.8 without explicit approval"), and a STOP-if-worktree-fails rule. This matches the anchor-5 pattern of explicit checkpoints with feedback loops.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the single SKILL.md is well-sectioned with one-level, clearly-signaled references to sibling devflow skills — never nested. It is anchor 4 rather than 5 only because the duplicated content across the three closing sections could be consolidated, a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

83%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: it states a precise trigger ("Use when driving a single already-specced ticket"), enumerates the concrete phase sequence collapsed into one session, and delimits its niche against sibling devflow skills. Its only weaknesses are devflow-internal jargon and slightly incomplete coverage of what the skill produces.

DimensionReasoningScore

Specificity

"a quick ambiguity-only brainstorm, then spec, plan, and lock-tests back-to-back, spawning a new session only for the execute phase" names several specific, scoped actions. It sits at anchor 4 rather than 5 because it does not comprehensively state what each phase produces, and above anchor 3 because it lists more than 1-2 concrete actions.

4 / 5

Completeness

"Use when driving a single already-specced ticket through devflow in one session" explicitly answers when, and the back-to-back phase sequence plus single execute spawn explicitly answers what. This matches the anchor-5 example structure of concrete what plus explicit trigger clause.

5 / 5

Trigger Term Quality

Natural terms a user would say are present ("ticket", "devflow", "spec", "plan", "tests", "execute"), giving good keyword coverage. A few natural phrases are missing and some jargon ("specced", "lock-tests") is assumed, so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — already-specced single tickets and "the per-ticket driver that orchestrate-epic invokes" — distinguishing it from greenfield/new-feature devflow skills. Minor overlap risk remains with the general devflow pipeline skills that share its trigger vocabulary, fitting anchor 4.

4 / 5

Total

17

/

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
AndreJorgeLopes/devflow
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.