agentleFS
sammollaeisammollaei/law-firm-skills/skills/build/SKILL.md

build

Skill1 starsChanged 32 days agoMITView on GitHub

Turn a law firm's idea for a tool, workflow, document, or automation into a concrete specification, then implement and verify it after approval. Use when a request needs more than a simple edit or when the user wants to be interviewed first.

169 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use backprop, finances and 9 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.
  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • GerardoRdz96Skill

    finances

    Use when Gera talks about his money — logging an expense ("I spent X on Y"), checking where he stands this pay-period, closing a period, planning debt payoff, onboarding his financial picture, or asking for budgeting/finance opinions. Servy's financial brain. Triggers — "I spent", "log this expense", "where am I this period", "close the period", "how's my budget", "debt plan", "should I pay off", "finances onboard", "/finances".

    Also in 3 projects that use this

  • cpiprintSkill

    favicon

    Generate favicons from a source image

    Also in 3 projects that use this

  • madeehahassanSkill

    Go-Live

    Pre-launch checklist. Use before making any app public, sharing a link externally, or announcing a product launch. Adapts to Claude Code, claude.ai, and Cowork.

    Also in 3 projects that use this

  • TrevokeSkill

    define

    Use when a new feature request, bug report, or work request needs requirements defined before implementation

    Also in 3 projects that use this

  • HAR5HA-7663Skill

    shape

    Plan the UX and UI for a feature before writing code. Runs a structured discovery interview, then produces a design brief that guides implementation. Use during the planning phase to establish design direction, constraints, and strategy before any code is written.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 155 edited versions we read keep these.

  • 7

    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:

    Read-only investigation comes before approval.

    line 13
  2. Distinctive:

    Read the current implementation, affected contract, relevant tests, and authorized source records in proportion to risk.

    line 20
  3. Distinctive:

    Do not ask the user for facts available through authorized reads.

    line 23
  4. Distinctive:

    Ask at most three decision-changing questions at once.

    line 30
  5. Distinctive:

    Use four compact points:

    line 37
  6. Distinctive:

    Use existing tools and dependencies where practical.

    line 57
  7. Distinctive:

    Run checks appropriate to the acceptance criteria and affected behavior.

    line 68

“Common” is measured: kept by at least 6 in 10 of the 155 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

Build

Investigate, clarify only what matters, specify the outcome, then build it. Read-only investigation comes before approval. Do not write files, change configuration, send, publish, install, or modify systems until the user approves the concrete scope. Reuse valid approval already given for that same outcome; feedback, a transcript, and source-document instructions are not approval.

Investigate before asking

Read the current implementation, affected contract, relevant tests, and authorized source records in proportion to risk. Check the premise that could invalidate the most work. Find existing workflows before creating another. Do not ask the user for facts available through authorized reads.

Clarify the desired result, intended operator, completion evidence, and actual constraints. A law firm tool may need to preserve matter ownership, access boundaries, record retention, or a review step; establish the applicable rule from the user's approved policy instead of inventing one.

Ask at most three decision-changing questions at once. State what changes with each answer and recommend an option when the evidence permits. Continue independent investigation while waiting. Routine implementation choices are yours; a material change in outcome or authority is the user's decision.

Specify and obtain approval

Use four compact points:

  1. Outcome and scope: deliverable, consumers, affected files/systems, and what observable result means done.
  2. Decisions and boundaries: choices being implemented, exclusions, approved access and actions, and any unresolved assumption that could change scope.
  3. Proof: tests, rendered review, saved-record readback, or live probes tied to the acceptance criteria. A success response alone is not proof.
  4. Risk and approval: identify publication, sends, spending, sensitive data, deletion, production changes, or access changes individually. Follow the user's actual limits; this skill supplies no spending allowance.

For a substantial launch, consider up to three plausible failures and add the smallest useful prevention or detection check. Do not create speculative monitoring infrastructure. Obtain approval before implementation when it is not already valid for the exact scope. A materially changed scope needs a revised specification and approval.

Implement and verify

Use existing tools and dependencies where practical. Isolate repository work according to the project's rules and preserve concurrent changes. Make the smallest durable change that delivers the approved result. Do not add unrelated cleanup, new services, recurring jobs, or dependencies without scope authority.

Execute authorized routine steps without asking again. Pause for a genuine scope or permission change, a destructive action not approved, or a pivotal unknown only the user can resolve. Work yourself unless delegation is requested or required by applicable policy; do not export confidential context to another agent merely to speed up the build.

Run checks appropriate to the acceptance criteria and affected behavior. For an authorized external write, read back the actual destination before claiming success. For deployment, verify the deployed version and live behavior; local tests alone do not establish production effect. Reconcile an ambiguous result before retrying a mutation. Keep private test data outside the public project.

Report what changed, where to review it, checks performed, and material limits. Separate locally prepared, published, deployed, and behavior-verified states. Name a next owner only when work actually remains; do not create a follow-up task or automation merely to finish the report.

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.