Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

deft-directive-feedback

Étoiles28

Forks11

Mis à jour7 juillet 2026 à 18:48

Batched session-end gap escalation for directive consumers. Collects friction/gap reports, drafts deduped framework-gap issues against deftai/directive, and files upstream only after explicit operator confirmation. Gated on plan.policy.valueFeedback upstreamPrompt.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

deftai

deftai/directive

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	deft-directive-feedback
description	Batched session-end gap escalation for directive consumers. Collects friction/gap reports, drafts deduped framework-gap issues against deftai/directive, and files upstream only after explicit operator confirmation. Gated on plan.policy.valueFeedback upstreamPrompt.

Deft Directive Feedback -- gap escalation to upstream

Conversational batched flow for filing framework gaps discovered during consumer sessions. Mirrors the confirmation gate from deft-directive-article-review -- the agent drafts and dedups; the operator approves before any upstream issue is created.

Legend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.

When to Use

Session end when friction:* ledger signals or operator reports a directive shortfall
Operator says "file this upstream", "report a framework gap", or "directive feedback"
After enabling plan.policy.valueFeedback.upstreamPrompt during onboarding

Preconditions

! Run only from a consumer project -- the filing path no-ops inside the directive maintainer repo
! plan.policy.valueFeedback.upstreamPrompt MUST be ON (task policy:show --field=valueFeedback)
⊗ File upstream issues without explicit operator confirmation
⊗ Invoke when valueFeedback.enabled is OFF

Phase 1 -- Collect (batched)

! Gather concrete gap reports from the session: what was expected, what happened, and minimal reproduction context
! Batch multiple friction items into one upstream issue when they share a root cause; otherwise prepare separate drafts
~ Prefer attributed phrasing ("encoding gate blocked a valid file") over vague quality claims

Phase 2 -- Draft + dedup

! For each candidate report, run a dry draft:

task feedback:file -- --summary "<one-line summary>" --context "<session context>" --expected "<expected>" --actual "<actual>" --notes "<optional>"

! Read the printed draft title/body with the operator before proceeding
! If the command reports a duplicate open issue, STOP and link the existing issue instead of filing again
⊗ Proceed past a duplicate-detection block without operator override

Phase 3 -- Confirm + file

! Present the final draft and ask for explicit yes/no confirmation
! Only after approval, re-run with --confirm:

task feedback:file -- --summary "<one-line summary>" --context "<session context>" --expected "<expected>" --actual "<actual>" --confirm

! Print the filed issue URL to the operator
⊗ Use Closes/Fixes/Resolves in the upstream body -- use Refs #1709 only

Phase 4 -- Handoff

~ Record the upstream issue URL in the session handoff or continue checkpoint if the operator tracks follow-ups locally
~ Return to the prior workflow; gap escalation does not block story completion

Anti-Patterns

⊗ Filing from the maintainer framework repo (consumer-only guard)
⊗ Skipping dedup review when the command reports an existing open issue
⊗ Treating --confirm as implicit from broad session approval -- require an explicit filing confirmation step

Plus depuis ce dépôt

même dépôt

deft-directive-release

deftai/directive

Cut a v0.X.Y release of the deft framework safely. Use when the user says "release", "cut release", "v0.X.Y", or "publish release" -- to walk an 8-phase workflow that pre-flights, runs an end-to-end rehearsal against a temp repo, lands a draft GitHub release (npm ships irrevocably at tag push), optionally QA's draft assets, then publishes the GitHub release or rolls back. Re-uses the deft-directive-swarm Phase 6 Step 5 Slack announcement template.

2026-07-1828

deft-directive-build

deftai/directive

Build a project from scope xBRIEFs following Deft Directive framework standards. Use after deft-directive-setup has generated the project definition, or when the user has story xBRIEFs in xbrief/active/ ready to implement. Handles scaffolding, implementation, testing, and quality checks phase by phase.

2026-07-1628

deft-directive-refinement

deftai/directive

Conversational refinement session. Ingests external work items into xBRIEF proposed/ scope, deduplicates via origin references, evaluates proposals with the user, reconciles stale origins, and promotes/demotes scopes through the lifecycle using deterministic task commands.

2026-07-1628

deft-directive-triage

deftai/directive

Triage-cache hygiene and "what's next?" work selection (ordered plan or ranked queue) -- the agent-facing playbook for syncing the triage cache, classifying candidates, presenting a ranked queue or binding to an active plan-sequence, walking per-item decisions (accept / reject / defer / needs-ac / mark-duplicate), and auditing the session. Use when the operator asks what to work on next, wants to build a cohort, work the cache, or run a triage hygiene pass.

2026-07-1628

deft-directive-swarm

deftai/directive

Parallel local agent orchestration. Use when running multiple agents on story-level xBRIEFs simultaneously — to scan active/ for allocatable work, set up isolated worktrees, launch agents with proven prompts, monitor progress, handle stalled review cycles, and close out PRs cleanly.

2026-07-1628

deft-directive-review-cycle

deftai/directive

Greptile / bot reviewer response and PR-shepherding workflow. Use when running a review cycle or babysitting a PR to merge-ready -- audit process prerequisites, fetch bot findings, fix all issues in a single batch commit, and exit cleanly when no P0 or P1 issues remain. Supersedes Cursor global babysit on Deft-managed repos (#2261).

2026-07-1528

name	deft-directive-feedback
description	Batched session-end gap escalation for directive consumers. Collects friction/gap reports, drafts deduped framework-gap issues against deftai/directive, and files upstream only after explicit operator confirmation. Gated on plan.policy.valueFeedback upstreamPrompt.

Deft Directive Feedback -- gap escalation to upstream

Legend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.

When to Use

Session end when friction:* ledger signals or operator reports a directive shortfall
Operator says "file this upstream", "report a framework gap", or "directive feedback"
After enabling plan.policy.valueFeedback.upstreamPrompt during onboarding

Preconditions

! Run only from a consumer project -- the filing path no-ops inside the directive maintainer repo
! plan.policy.valueFeedback.upstreamPrompt MUST be ON (task policy:show --field=valueFeedback)
⊗ File upstream issues without explicit operator confirmation
⊗ Invoke when valueFeedback.enabled is OFF

Phase 1 -- Collect (batched)

! Gather concrete gap reports from the session: what was expected, what happened, and minimal reproduction context
! Batch multiple friction items into one upstream issue when they share a root cause; otherwise prepare separate drafts
~ Prefer attributed phrasing ("encoding gate blocked a valid file") over vague quality claims

Phase 2 -- Draft + dedup

! For each candidate report, run a dry draft:

task feedback:file -- --summary "<one-line summary>" --context "<session context>" --expected "<expected>" --actual "<actual>" --notes "<optional>"

! Read the printed draft title/body with the operator before proceeding
! If the command reports a duplicate open issue, STOP and link the existing issue instead of filing again
⊗ Proceed past a duplicate-detection block without operator override

Phase 3 -- Confirm + file

! Present the final draft and ask for explicit yes/no confirmation
! Only after approval, re-run with --confirm:

task feedback:file -- --summary "<one-line summary>" --context "<session context>" --expected "<expected>" --actual "<actual>" --confirm

! Print the filed issue URL to the operator
⊗ Use Closes/Fixes/Resolves in the upstream body -- use Refs #1709 only

Phase 4 -- Handoff

~ Record the upstream issue URL in the session handoff or continue checkpoint if the operator tracks follow-ups locally
~ Return to the prior workflow; gap escalation does not block story completion

Anti-Patterns

⊗ Filing from the maintainer framework repo (consumer-only guard)
⊗ Skipping dedup review when the command reports an existing open issue
⊗ Treating --confirm as implicit from broad session approval -- require an explicit filing confirmation step