deft-directive-spec-reconstruct SKILL.md skillA

deft-directive-spec-reconstruct from deftai/directive is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add deftai/directive/deft-directive-spec-reconstruct@git:20261006.79339c8

Pins git:20261006.79339c8 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
deftai/directive
Path
content/skills/deft-directive-spec-reconstruct/SKILL.md
Versions recorded
2
Latest version
git:20261006.79339c8, committed Oct 6, 2026
First version recorded
Oct 5, 2026
Size
5,705 bytes
Repository stars
31
License
a license file GitHub does not identify

Brownfield specification reconstruction + advise|shadow|enforce drift guard (#1589 / #5350). Draft-only synthesis from completed xBRIEFs + #1595 codebase MAP; never auto-promotes. Use when reconstructing a failed/stale spec, recovering requirements, or checking semantic spec drift. Do NOT trigger on ordinary spec:render / spec:validate / verify:spec-prd-fresh.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

<!-- AUTO-GENERATED by task packs:render -- DO NOT EDIT MANUALLY -->
<!-- Purpose: rendered skill -->
<!-- Source of truth: packs/skills/skills-pack-0.1.json -->
<!-- Regenerate with: task packs:render -->
<!-- Edit the source, not this file. Slice instead of loading every SKILL.md: task packs:slice skills by-trigger --trigger <kw> (or list) -->

# Spec Reconstruct + Drift Guard (#1589 / #5350)

Recover a trustworthy project specification from completed xBRIEFs, then audit drift under advise|shadow|enforce.

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

## When to Use

- Spec baseline has failed or drifted after RFC/ADR/feature landings
- Operator says "reconstruct spec", "recover spec", or "spec is stale/failed"
- Auditing semantic drift via `verify:spec-drift`
- ⊗ Ordinary `spec:render` / `spec:validate` / `verify:spec-prd-fresh` freshness work

## Live surfaces (re-authored)

- Policy: `packages/core/src/policy/spec-guard.ts` via `plan["x-directive/policy"].specGuard`
- Reconstruct: `packages/core/src/spec-reconstruct/` + `task spec:reconstruct`
- Drift: `packages/core/src/verify-source/spec-drift.ts` + `task verify:spec-drift`
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add deftai/directive/deft-directive-spec-reconstruct@sha256:8b14b9b73eef3dcf

The line at the top of this page pins the label git:20261006.79339c8, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_q7i6yr2fzm6ahxl3.svg)](https://markdownregistry.com/a/art_q7i6yr2fzm6ahxl3)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Oct 5, 2026 and Oct 6, 2026, about one every day.

versioncommittedcommitsizeaudit
git:20261006.79339c8 latest2026-10-06 79339c8 5,705 BA view · diff
git:20261005.3456c672026-10-05 3456c67 4,341 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5705 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

deftai/directive · 31 stars · license a license file GitHub does not identify · pushed 2026-10-22 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_q7i6yr2fzm6ahxl3
GET https://markdownregistry.com/api/v1/resolve?ref=deftai/directive/deft-directive-spec-reconstruct
GET https://markdownregistry.com/api/v1/blob/8b14b9b73eef3dcfaee4d8b5f741b39f62492acdfb05137179efd90e5500c886

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from deftai/directive

deft-directive-build SKILL.md skill
deftai/directive · .agents/skills/deft-directive-build/SKILL.md · Build a project from scope vBRIEFs following Directive standards.
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-interview SKILL.md skill
deftai/directive · .agents/skills/deft-directive-interview/SKILL.md · Deterministic structured Q&A interview skill (one question per turn).
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-portfolio-priority SKILL.md skill
deftai/directive · .agents/skills/deft-directive-portfolio-priority/SKILL.md · Pre-promotion portfolio prioritization across competing open RFCs/issues.
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-pre-pr SKILL.md skill
deftai/directive · .agents/skills/deft-directive-pre-pr/SKILL.md · Iterative pre-PR quality loop (Read-Write-Lint-Diff-Loop).
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-refinement SKILL.md skill
deftai/directive · .agents/skills/deft-directive-refinement/SKILL.md · Structured refinement workflow: triage issues and update the roadmap.
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-review-cycle SKILL.md skill
deftai/directive · .agents/skills/deft-directive-review-cycle/SKILL.md · Greptile bot reviewer response workflow for autonomous PR review cycles.
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-setup SKILL.md skill
deftai/directive · .agents/skills/deft-directive-setup/SKILL.md · Set up a new project with Directive framework standards.
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-swarm SKILL.md skill
deftai/directive · .agents/skills/deft-directive-swarm/SKILL.md · Parallel local agent orchestration with isolated worktrees.
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-sync SKILL.md skill
deftai/directive · .agents/skills/deft-directive-sync/SKILL.md · Session-start framework sync and alignment check.
git:20261021.cc4bd5d · audit A · 31 stars
deft SKILL.md skill
deftai/directive · .agents/skills/deft/SKILL.md · Apply Directive framework standards for AI-assisted development.
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-build SKILL.md skill
deftai/directive · .claude/skills/deft-directive-build/SKILL.md · Build a project from scope vBRIEFs following Directive standards.
git:20261021.cc4bd5d · audit A · 31 stars
deft-directive-interview SKILL.md skill
deftai/directive · .claude/skills/deft-directive-interview/SKILL.md · Deterministic structured Q&A interview skill (one question per turn).
git:20261021.cc4bd5d · audit A · 31 stars

Every file in deftai/directive

Browse by kind, by grade A, or by owner.