Automated summary
Drafts evidence-based SDD reports and Git/hosted artifacts such as task issues, commit messages, pull request descriptions, and release notes.
Strengths
- Clearly separates planned, performed, verified, and blocked statements, and prevents intentions from being presented as completed results.
- Routes each output type to a dedicated reference for Git drafts, completion reports, releases, document QC, and review campaigns.
- Requires supporting evidence and actually resolved issue references, and asks for missing facts to be stated before publication.
- Enforces consistent Markdown formatting and precise task-linked commit subject rules.
Limitations
- Limited to drafting: it does not create commits, pull requests, or issues, and does not update task status.
- Depends on SDD project structures and internal references (sdd-manage, sdd-forge), so it is less self-contained outside that setup.
- Does not automatically validate evidence; manual checking is still required.
Use it when drafting an SDD task issue, commit, PR description, status or release report, or review campaign artifacts from actual evidence.
Do not use it to perform Git or hosted operations, change task status, or write general documentation unrelated to SDD evidence and workflows.
Security analysis
SafeThe skill contains only prose guidance for drafting reports, commit messages, PR descriptions, and release notes. It declares no tools and performs no execution, network access, secret handling, or filesystem mutation. Its references to sibling reference files and bundled dependencies are ordinary documentation routing, not commands, and the text contains no attempt to override or influence this assessment.
No concerns found
How this analysis is madeExamples
Draft a task issue for [task-id] that adds OAuth login to the admin console. Base it on the TASKS entry, SPEC, and current changes; separate the acceptance plan from verified results.Prepare a pull request description for the feature branch implementing [feature]. Summarize What, Why, Verification, and Result using the actual test output and Git diff, and flag any missing evidence.Draft curated Git release highlights and release notes for version 1.4.0 from the merged tasks and verification evidence, without claiming unverified results.name: sdd-report description: Use when drafting a task issue, Git commit message, pull request description, or evidence-backed task, milestone, phase or final implementation report, review/revision campaign plan or report, package preparation result, curated Git release highlights, release notes or release outcome for an SDD project. Adapt the summary to feature, bug, code health, performance, security, testing, documentation, integration, or compatibility work without inventing results.
Report SDD work
For Markdown output or document work within this skill's scope, apply the shared Markdown style: blank lines after headings and around top-level lists and code blocks, plus four-space structural indentation, including nested lists, with exactly one space after each list marker. This applies to direct calls as well as coordinated work; it does not expand editing or review authority.
Choose the requested output and load only its reference:
| Output | Load |
| --- | --- |
| First SDD commit disclosure/usage evidence (drafting only) | sdd-manage: skills/sdd-manage/references/repository-bootstrap.md (bundled dependency) |
| Planned task issue title and body, task/amendment or merge commit message, or pull request draft | drafts for hosted and Git objects |
| Task, milestone, phase, final implementation, branch boundary, or interrupted-work status report | completion reports |
| Package/workflow preparation, Git release highlights, release notes or release outcomes | package and release reporting |
| Adjacent SPEC/PLAN/TASKS preparation QC reports and appended correction/recheck sections | document QC reports |
| Review plan/report or revision plan/report, including focused prompt-driven review | campaign artifacts |
| Kind-specific emphasis and reusable What, Why, Verification, Result patterns | change kinds |
Use the owning TASKS or active FEATURE-TASKS entry, applicable design, SPEC, PLAN, and layout, actual changes, verification output, and Git evidence appropriate to the requested output. Obtain hosted issue references from sdd-forge when available; a guessed issue number is never acceptable. Separate planned, performed, verified, and blocked statements. State missing or limited evidence plainly; do not turn an example, unchecked task, or intended benchmark into a completed result. Follow project-specific title and reporting conventions where they exist.
Compose only the requested text or structured draft. Keep a concise shared core of What, Why, Verification, and Result, varying the labels and optional sections to suit the actual change. For a planned issue, Verification is an acceptance or check plan and Result is an intended outcome, not a completed claim. Emoji labels are optional presentation, not required metadata.
Task-associated subjects must begin with exactly one owning [<task-id>] marker and an imperative description; use the task subject rules and return composition conflicts to the commit owner. Do not invent IDs for non-task campaign, preparation or merge work.
This skill drafts reports and messages. The active implementation or steering workflow owns its work commits and task status; sdd-manage coordinates other persistence and explicit boundary merges, sdd-forge owns hosted issue/milestone mutations, and any future PR workflow owns PR creation or merge. A draft does not grant authorization for those actions or establish task completion. Return the draft, source task IDs and issue references actually resolved, evidence used, and any facts still needed before publication.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/sdd-work-reporting-mvda896p/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/sdd-work-reporting-mvda896p' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/sdd-work-reporting-mvda896p/download' --output '.skill-downloads/sdd-work-reporting-mvda896p/SKILL.md.part' && mv '.skill-downloads/sdd-work-reporting-mvda896p/SKILL.md.part' '.skill-downloads/sdd-work-reporting-mvda896p/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/sdd-work-reporting-mvda896p/SKILL.md' && test -s '.skill-downloads/sdd-work-reporting-mvda896p/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/sdd-report' && cp -R '.skill-downloads/sdd-work-reporting-mvda896p' '.claude/skills/sdd-report'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/sdd-work-reporting-mvda896p'openskills read 'sdd-work-reporting-mvda896p'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/sdd-work-reporting-mvda896p/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.