CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

phase-handoff

Hand off between phases of the devflow new-feature pipeline. Writes a frozen-state file, marks a chapter, sets the terminal title, gates on a one-click AskUserQuestion unless `--unattended` is passed, then spawns a new session for the next phase via `mcp__ccd_session__spawn_task` so it shows up in the Claude Desktop sidebar with a deterministic title.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

An exceptionally actionable, well-validated workflow — concrete commands, exact tool payloads, guarded commits, explicit failure paths, and a user gate — that scores at the top of actionability and workflow clarity. Its costs are token efficiency and structure: the same three design facts are restated three to four times across the intro, steps, and Important section, and everything (worked example, pruning guide) is inlined in one long file with no reference files. Consolidating the repeated rationale and splitting the example/pruning material into references would raise both dimensions.

Suggestions

State each core fact once — e.g. consolidate the fresh-worktree/durability/group-placement rationale (currently repeated in the intro, step 4b/9, step 11's output, and Important) into a short "Key constraints" block and reference it from the steps instead of restating it.

Move the worked example prompt (step 9) and the orphan-worktree pruning guide (Important) into reference files (e.g. references/example-prompt.md, references/orphan-pruning.md) and link to them, keeping SKILL.md as a lean overview.

Trim the multi-line justification comments (e.g. the husky/--no-verify rationale and the wrapper-policy paragraph, which also appears in Important) to one-line pointers; the operational command matters more than the repeated motivation.

DimensionReasoningScore

Conciseness

The body is mostly skill-specific knowledge Claude cannot know (spawn_task worktree behavior, devflow wrapper policy, husky bypass), so it avoids explaining known concepts — but the same core facts are restated repeatedly: the "spawned session lands in the wrong worktree" warning appears in the intro, step 9's template, the worked example, and the step-11 output; the durability/commit rationale appears in intro point 2, step 4b, and Important; group-placement limits appear three times. This fits the level-3 anchor ("mostly efficient but ... could be tightened") rather than 2, because the verbosity is redundant restatement of bespoke facts rather than padded generic explanation, and rather than 4 because the duplication is more than minor.

3 / 5

Actionability

Guidance is fully executable throughout: copy-paste bash for branch/worktree detection, slug sanitization, MR detection via gh/glab, the commit-with-guardrails block; an exact `mark_chapter` payload; a printf terminal-title escape; the exact AskUserQuestion options and exact output strings to print; and a complete spawn prompt template plus a fully worked MES-4282 example. This matches the level-5 anchor (copy-paste ready, examples cover the common cases) and exceeds level 4, which allows minor gaps — the only placeholders are inherently run-specific values.

5 / 5

Workflow Clarity

Steps 1–11 are explicitly sequenced with strong validation checkpoints and feedback loops: STOP if on the wrong branch before committing (step 1); a guarded no-op vs. real-failure distinction in step 4b where a failed commit prints a loud WARNING rather than passing silently; append-not-overwrite re-entry handling; the `--no-handoff` and `--unattended` escape hatches; and a user confirmation gate before the spawn. This matches the level-5 anchor (explicit validation, error recovery, escape hatches) and is above level 4, whose "minor validation gaps" are absent.

5 / 5

Progressive Disclosure

There are no bundle files (no references/, scripts/, or assets/), so everything lives in one ~290-line SKILL.md. Internal structure is good (numbered steps, tables, an Important section), but content that belongs in separate files is inlined: the 35-line worked example duplicates the template, and the orphan-worktree pruning guide and wrapper-policy rationale are embedded in Important. This matches the level-3 anchor ("some structure ... content that should be separate is inline"); it is above 2 because structure is far from minimal, and below 4 because there are no well-signaled external references and the file is well over the simple-skill threshold.

3 / 5

Total

16

/

20

Passed

Description

75%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 highly specific, well-voiced description that names every concrete action and the exact tooling, making it virtually conflict-free. Its one real weakness is the absent "Use when..." trigger clause — invocation timing is only weakly implied — which caps completeness at the midpoint. Adding an explicit trigger sentence naming the pipeline phases would lift it to the top band.

Suggestions

Append an explicit trigger clause, e.g. "Use at the end of the spec, plan, or lock-tests phase of a devflow new-feature run, when one phase completes and the next should start in a fresh session."

Include the phase names users would actually say ("spec", "plan", "lock-tests", "implementation") as trigger keywords so the skill matches natural requests like "move on to the plan phase".

Optionally mention the `--unattended` / `--no-handoff` escape hatches in trigger terms (e.g. "use --unattended for CI-style runs") to cover the unattended invocation scenario.

DimensionReasoningScore

Specificity

Quotes five-plus concrete actions — "Writes a frozen-state file", "marks a chapter", "sets the terminal title", "gates on a one-click AskUserQuestion unless `--unattended` is passed", "spawns a new session ... via `mcp__ccd_session__spawn_task`" — naming the exact tool and even the output surface ("Claude Desktop sidebar with a deterministic title"). This matches the anchor for multiple specific concrete actions with comprehensive coverage, and exceeds the level-4 anchor ("minor gaps in coverage") because every stage of the skill's operation is named. Third-person voice throughout, so no voice penalty applies.

5 / 5

Completeness

The "what" is explicit and detailed (frozen-state file, chapter mark, terminal title, gate, spawn), but there is no "Use when..." clause or equivalent explicit trigger guidance — when to invoke is only weakly implied by "Hand off between phases of the devflow new-feature pipeline". Per the judging guideline, a missing 'Use when' clause caps completeness at 3, which is exactly the anchor "Has a clear 'what' but 'when' is missing or only weakly implied"; it is not 4 because no 'when' is present at all, and not 2 because the 'what' is fully concrete.

3 / 5

Trigger Term Quality

Natural terms a user would say are present — "Hand off", "phases", "next phase", "spawn a new session", "pipeline" — plus distinctive domain anchors ("devflow new-feature pipeline", "Claude Desktop sidebar"). It falls at the level-4 anchor (good keyword coverage, a few natural terms missing) rather than 5 because common variations a user might say — "spec", "plan", "implementation", "phase transition", "continue" — are absent; it is above level 3 since the primary natural phrases users would utter for this need are all there.

4 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche with minimal conflict risk: it names a specific pipeline ("devflow new-feature pipeline"), a specific MCP tool (`mcp__ccd_session__spawn_task`), and specific behaviors (frozen-state file, chapter marking, one-click gate) that no generic handoff/session skill would share. This matches the level-5 anchor ("Clear niche with distinct triggers; minimal conflict risk") and is above level 4, which requires some residual overlap with closely related skills — none is plausible here.

5 / 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

Path

skills/phase-handoff/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.