agentleFS
SebaBolerSebaBoler/vanguard/skills/tech-spec/SKILL.md

tech-spec

Skill5 starsChanged 21 days agoMITView on GitHub

Use when a task is under-specified and needs a written technical specification BEFORE any code is written or changed. This skill only researches and documents — it never edits source files. Do not invoke for implementing, reviewing, or simplifying existing code.

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use bro, coding-standards and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    bro

    Re-explain the previous assistant message in a much simpler way, for when the reply made you go 'bro what'. Use /bro to get a simpler version of the last answer in Plain Language + Chicago Manual of Style, with diagrams where they help.

    Also in 4 projects that use this

  • nanvixSkill

    coding-standards

    Detailed Nanvix coding, documentation, and review standards across Rust, C/C++, Python, and Shell. Use this when asked to implement or review code quality conventions.

    Also in 4 projects that use this

  • MicrosoftSkill

    jira

    Jira issue workflows for search, issue updates, transitions, comments, field discovery, and interactive credential setup via the Jira REST API. Use when you need to configure Jira access, search with JQL, inspect an issue, create or update work items, move an issue between statuses, post comments, or discover required fields for issue creation.

    Also in 3 projects that use this

  • asterkinSkill

    adr

    Create Architecture Decision Records (ADRs) following project standards. Guides template usage, process, and best practices for documenting architecturally significant decisions.

    Also in 3 projects that use this

  • GoogleSkill

    domain-modeling

    Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

    Also in 3 projects that use this

  • NVIDIASkill

    deep-research

    Queue deep, multi-step research and analysis tasks to the DeepAgents worker. Supports execution depth presets, request-specific rubrics, SubAgent delegation, and RubricMiddleware cross-validation.

    Also in 3 projects that use this

  • +1 more from microsoft

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not edit, create, or delete any source files.

    line 9
  2. Distinctive:

    Test cases and scenarios that must pass, including edge cases, failure paths, and integration boundaries.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Tech Spec

Research the codebase read-only and produce a precise technical specification for the given task. Do not edit, create, or delete any source files.

Sections to include

Problem

What exactly needs to be solved and why. Identify the gap between the current state and the desired state. Name the stakeholders and the concrete pain point. Check the ticket's premise against the code first: if the proposed mechanism already exists, or the real gap is elsewhere, say so here and re-scope the spec to the actual gap rather than specifying a duplicate.

Architecture

Components involved, interfaces changed or added, data flows, and integration points with the rest of the system. Include sequence or data-flow sketches if the interaction is non-trivial.

Acceptance Criteria

Numbered, testable conditions that define done. Each criterion must be verifiable without ambiguity from the repository state and the diff alone: a command that exits 0, a test that passes, a file that contains or no longer contains something. Never require an artifact outside the repo (a file under /tmp, a captured baseline), a CI run, or a particular commit message — the autonomous implementer controls none of those (the factory writes the commit message itself from the task title), and such a criterion only turns a complete change into a "partial scope" delivery. Put any baseline numbers the implementer must match into the spec itself. The one PR-body criterion that is allowed is the one CLAUDE.md prescribes: when the task needs a CI-config edit the agent must not make, the AC is "the PR body describes the needed edit for a human to apply".

Tests

Test cases and scenarios that must pass, including edge cases, failure paths, and integration boundaries. Name the test file(s) and key scenarios explicitly.

Risks

Known unknowns, edge cases, backward-compatibility concerns, and failure modes. Call out any assumption that, if wrong, would invalidate the design.

Performance / Scalability

Throughput and latency expectations, growth projections, and any bottleneck or scaling limit introduced or removed by the change.

Output format

Wrap the complete specification in <tech_spec>...</tech_spec>. End with <promise>COMPLETE</promise>.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.