Show Me Your Work Decision Log
cursor/plugins
Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.
SDD phase-gate review — enforces the SDD pipeline's gated structure by reviewing specification artifacts before the next phase can proceed.
MITAuto-check passed
Install Sdd Review
$ npx skills add magnus919/hermes-profiles --skill sdd-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install magnus919/hermes-profiles sdd-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/sdd-review .claude/skills/sdd-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "sdd-review" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/sdd-review into .claude/skills/sdd-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/magnus919/hermes-profiles/tree/main/skills/sdd-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add magnus919/hermes-profiles --skill sdd-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install magnus919/hermes-profiles sdd-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/sdd-review .agents/skills/sdd-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sdd-review" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/sdd-review into .agents/skills/sdd-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add magnus919/hermes-profiles --skill sdd-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install magnus919/hermes-profiles sdd-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/sdd-review .cursor/skills/sdd-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sdd-review" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/sdd-review into .cursor/skills/sdd-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/magnus919/hermes-profiles.git --path skills/sdd-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add magnus919/hermes-profiles --skill sdd-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install magnus919/hermes-profiles sdd-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/sdd-review .gemini/skills/sdd-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sdd-review" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/sdd-review into .gemini/skills/sdd-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install magnus919/hermes-profiles sdd-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add magnus919/hermes-profiles --skill sdd-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/sdd-review .github/skills/sdd-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sdd-review" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/sdd-review into .github/skills/sdd-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add magnus919/hermes-profiles --skill sdd-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install magnus919/hermes-profiles sdd-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/magnus919/hermes-profiles.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/sdd-review .opencode/skills/sdd-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sdd-review" agent skill from https://github.com/magnus919/hermes-profiles/tree/main/skills/sdd-review into .opencode/skills/sdd-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sdd-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
sdd-review- GitHub stars
- 289
- Token cost
- ~1.8k tokens
- SKILL.md length
- 801 words
- Files
- 6 (incl. references)
- Skills in repo
- 31
- Repo updated
- First seen
- Licence
- MIT
At a glance
SDD phase-gate review — enforces the SDD pipeline's gated structure by reviewing specification artifacts before the next phase can proceed.
- Works in 3 steps: Document the disagreement clearly — what… → Escalate to the orchestrator or human if… → MINOR and INFO disagreements are…
- Tasks that involve Human-in-the-loop approvals
- SKILL.md covers SDD Pipeline Position, Core Principle: The Gate Is…, Artifact-Pyramid Output:… and Loading Guidance, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Sdd Review is an agent skill from magnus919/hermes-profiles. SDD phase-gate review — enforces the SDD pipeline's gated structure by reviewing specification artifacts before the next phase can proceed. Produces artifact-pyramid-compliant gate decision reports. No phase passes without reviewed, approved artifacts.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/acceptance-review-patterns.md`, `references/implementation-review-patterns.md` and `references/phase-gate-methodology.md`).
The repository describes itself as: Curated Hermes Agent profiles for specialist swarms — opinionated, Hermes-optimized, artifact-pyramid native. The licence is MIT.
When your agent uses it
- Tasks that involve Human-in-the-loop approvals
Example prompts
- “/sdd-review”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Document the disagreement clearly — what the artifact says, what the reviewer found, why the author disagrees
- Escalate to the orchestrator or human if the finding is BLOCKING or CRITICAL
- MINOR and INFO disagreements are resolved by the reviewer's determination — the gate is not delayed for editorial preferences
What it can do on your machine
Read from SKILL.md and the folder at commit 867a555. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Sdd Review loads about 1.8k tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 801 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from magnus919/hermes-profiles at commit 867a555, republished under its MIT licence (© magnus919). 801 words, ~1,751 tokens.
Download SKILL.mdSave it as
.claude/skills/sdd-review/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- sdd-review
- description
- SDD phase-gate review — enforces the SDD pipeline's gated structure by reviewing specification artifacts before the next phase can proceed. Produces artifact-pyramid-compliant gate decision reports. No phase passes without reviewed, approved artifacts.
- version
- 1.0.0
- author
- Hermes Agent community
- license
- MIT
SDD Phase-Gate Review
Enforcing the SDD pipeline's gated structure: every artifact is reviewed before the next phase proceeds. This skill owns the Review gates between every pair of SDD phases.
SDD Pipeline Position
[SPECIFY] → REVIEW → [PLAN] → REVIEW → [TASKS] → REVIEW → [IMPLEMENT] → REVIEW → [VERIFY]
↑ ↑ ↑ ↑ ↑ ↑ ↑ ↑
└─────────┘ └────────┘ └─────────┘ └──────────┘
Gate 1: Spec Gate 2: Plan Gate 3: Tasks Gate 4: ImplementationEvery gate asks the same question: "Is the artifact for this phase complete, correct, and unambiguous enough for the next phase to proceed safely?"
Core Principle: The Gate Is the Quality Mechanism
In SDD, quality is not enforced by code review — that's too late. Quality is enforced by the phase gate. A defect caught at Gate 1 (spec review) costs minutes to fix. The same defect caught at Gate 4 (implementation review) costs hours — the implementation may need to be discarded and rewritten against a corrected spec.
This skill is deliberately strict. Its job is not to be agreeable; its job is to protect downstream phases from upstream artifacts that would waste their time.
Artifact-Pyramid Output: REVIEW.md
Phase-gate review reports follow the artifact-pyramid structure:
| Layer | Content | File |
|---|---|---|
| L1 | Gate decision — APPROVED / CONDITIONS / REJECTED, one-line rationale, blocking findings count | 00-index.md (entry point) |
| L2 | Review findings by category — spec completeness, task correctness, implementation compliance, verification gaps | Individual *.findings.md files |
| L3 | Per-finding dossiers — severity, location (artifact + section), recommendation, evidence, escalation path | dossiers/ directory |
| SOURCES | Cross-reference from each finding to the artifact section it evaluates | Footer of each file |
Loading Guidance
| Reference | When to load | File |
|---|---|---|
| Phase Gate Methodology | Before running any review — the four-gate structure, decision criteria, escalation paths | references/phase-gate-methodology.md |
| Spec Review Patterns | Reviewing a SPEC.md — completeness checks, ambiguity detection, testability assessment | references/spec-review-patterns.md |
| Implementation Review Patterns | Reviewing code against a spec — not general code review, but spec-compliance review | references/implementation-review-patterns.md |
| Acceptance Review Patterns | Reviewing verification results — assessing whether the verification report justifies a pass verdict | references/acceptance-review-patterns.md |
| Template | When to use | File |
|---|---|---|
| REVIEW.md | Producing a phase-gate review report | templates/REVIEW.md |
Trigger Conditions
Invoke this skill when:
- A SPEC.md has been authored and needs review before work decomposition begins (Gate 1)
- A TASK-PLAN.md has been produced and needs review before implementation starts (Gate 2)
- Implementation output needs spec-compliance review (Gate 3)
- A VERIFICATION.md report needs review before the pipeline delivers (Gate 4)
- An escalation has been raised about an earlier gate decision and needs re-review
The Four Gates
Gate 1: Spec Review
Reviews SPEC.md against the quality gates defined in sdd-authoring. Questions asked:
- Is every acceptance criterion testable?
- Are edge cases enumerated, not just implied?
- Are non-functional requirements specified with measurable thresholds?
- Is the scope boundary clear (explicit in-scope and out-of-scope)?
- Are data contracts and interface definitions sufficiently precise?
- Does any section leave room for the implementation agent to make an unguided assumption?
Verdict: APPROVED only if every question produces a clear "yes" or has an explicit remediation plan.
Gate 2: Plan Review
Reviews TASK-PLAN.md against the specification. Questions asked:
- Does every specification requirement map to at least one task?
- Are dependencies real and spec-derived, not invented?
- Is each task independently verifiable?
- Are task sizes appropriate for a single implementation session?
- Does the CLAUDE.md / AGENTS.md handoff accurately represent the spec and plan?
Verdict: APPROVED only if spec traceability is complete and dependency mapping is honest.
Show full SKILL.md (290 more words)Show less
Gate 3: Implementation Review
Reviews implementation output against the task plan. This is NOT a general code review — it does not assess code style, test coverage, or architectural elegance. It asks only:
- Does the implementation satisfy the acceptance criteria for each completed task?
- Are there any deviations from the spec that were not documented?
- Does the implementation produce correct results for all specified inputs?
- Are error states handled per the spec?
Verdict: APPROVED only if all completed task ACs are satisfied.
Gate 4: Acceptance Review
Reviews the VERIFICATION.md report. Questions asked:
- Are all spec ACs accounted for in the verification matrix (none missing)?
- Are FAIL verdicts correctly classified by severity?
- Are BLOCKING and CRITICAL failures accompanied by remediation plans?
- Is the overall compliance score sufficient for delivery?
Verdict: APPROVED only if no BLOCKING failures exist and all CRITICAL failures have documented exceptions or remediation plans.
Gate Decision Format
Every gate produces one of three verdicts:
| Verdict | Meaning | What happens next |
|---|---|---|
| APPROVED | Artifact passes all criteria. The next phase may proceed. | Deliver artifact to next phase |
| CONDITIONS | Artifact passes subject to specific remediations that do not require a full re-review | Deliver artifact + conditions list; next phase may proceed while conditions are resolved |
| REJECTED | Artifact fails one or more criteria. The current phase must produce a revised artifact. | Return artifact to current phase; no downstream work starts |
Escalation
When a reviewer and artifact author disagree on a finding, the escalation path is:
- Document the disagreement clearly — what the artifact says, what the reviewer found, why the author disagrees
- Escalate to the orchestrator or human if the finding is BLOCKING or CRITICAL
- MINOR and INFO disagreements are resolved by the reviewer's determination — the gate is not delayed for editorial preferences
© magnus919, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in skills/sdd-review of magnus919/hermes-profiles.
- SKILL.md
- references/acceptance-review-patterns.md
- references/implementation-review-patterns.md
- references/phase-gate-methodology.md
- references/spec-review-patterns.md
- templates/REVIEW.md
Open the folder on GitHubat commit 867a555
Compare with similar skills
Sdd Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Sdd Review this skillmagnus919/hermes-profiles | 289 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Show Me Your Work Decision Logcursor/plugins | 11k | 8 repos | ~1.6k | Automated safety check: Pass | None | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Iron Proxy Gateway for NanoClawnanocoai/nanoclaw | 31k | — | ~4.6k | Automated safety check: Notes | MIT | |
| Trigger.dev Agent Patternspapermark/papermark | 9.2k | — | ~2k | Automated safety check: Pass | Custom licence | |
| Code Implementationapache/shardingsphere | 21k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Darwin Skill Optimizer
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
Iron Proxy Gateway for NanoClaw
nanocoai/nanoclaw
Installs or refreshes Iron Proxy and its Iron Control web console for NanoClaw, with a local Docker setup, database, credentials and a human approval bridge.
Trigger.dev Agent Patterns
papermark/papermark
Patterns for building LLM agents on Trigger.dev tasks: prompt chaining, routing, parallel workers, orchestrator-workers, evaluator loops and human approval gates.
Code Implementation
apache/shardingsphere
Implement, fix, refactor, or remove repository code under required scope, non-regression, verification, and review gates.
Loop Constraints Enforcer
cobusgreyling/loop-engineering
Loads a project's loop-constraints.md before any other action and blocks pushes, edits or merges that violate the rules it defines.
More from magnus919/hermes-profiles
All 31 skills in this repoData Scientist
magnus919/hermes-profiles
PhD-level expertise in data science, statistics, and machine learning.
Brand Designer
magnus919/hermes-profiles
Create comprehensive brand identity documentation for any brand.
Sdd Authoring
magnus919/hermes-profiles
Specification authoring for AI-native SDD — writes formal specifications in structured formats (Gherkin, user stories, acceptance criteria), enforces spec quality gates, and produces…
Sdd Verification
magnus919/hermes-profiles
SDD acceptance criteria verification — maps specification acceptance criteria to tests, validates implementation output against spec requirements, and produces artifact-pyramid-compliant…
Sdd Work Decomposition
magnus919/hermes-profiles
SDD work decomposition — translates formal specifications into dependency-aware task plans with per-task acceptance criteria.
Artifact Pyramids
magnus919/hermes-profiles
Progressive disclosure for what AI agents produce. An agent skill from magnus919/hermes-profiles.
Questions about Sdd Review
What does Sdd Review do?
SDD phase-gate review — enforces the SDD pipeline's gated structure by reviewing specification artifacts before the next phase can proceed. Sdd Review is an agent skill from magnus919/hermes-profiles. SDD phase-gate review — enforces the SDD pipeline's gated structure by reviewing specification artifacts before the next phase can proceed.
When should I use Sdd Review?
Sdd Review fits situations like: tasks that involve Human-in-the-loop approvals.
How do I install Sdd Review in Claude Code?
Run `npx skills add magnus919/hermes-profiles --skill sdd-review -a claude-code`. Or copy the skill folder (skills/sdd-review in magnus919/hermes-profiles) into .claude/skills/sdd-review in your project. Claude Code loads it when a task matches its description.
How do I install Sdd Review in Codex?
Run `npx skills add magnus919/hermes-profiles --skill sdd-review -a codex`. Or copy the skill folder (skills/sdd-review in magnus919/hermes-profiles) into .agents/skills/sdd-review in your project. Codex loads it when a task matches its description.
Can I use Sdd Review in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add magnus919/hermes-profiles --skill sdd-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sdd-review, .gemini/skills/sdd-review, .github/skills/sdd-review and .opencode/skills/sdd-review in your project.
What does Sdd Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Sdd Review is instructions for the agent only.
Does Sdd Review access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Sdd Review safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Sdd Review use?
Sdd Review is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Sdd Review use?
About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.
What are the alternatives to Sdd Review?
Skills that share tags, products or a category with Sdd Review: Show Me Your Work Decision Log (cursor/plugins, 11k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), Iron Proxy Gateway for NanoClaw (nanocoai/nanoclaw, 31k stars) and Trigger.dev Agent Patterns (papermark/papermark, 9.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sdd Review?
magnus919 (a GitHub user) maintains it in magnus919/hermes-profiles, which has 289 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on June 27, 2026.
Source: magnus919/hermes-profiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.