Skip to content
Agentmart
Submit a tool

consolidate

Consolidate canonical product knowledge, ideas, behavior, decisions, increments, and evidence; route technical decisions and reconcile delivery, exposure, and…

Skill by BetoFrega

IndexedMIT
Write a review

Chalk Labs

Need help deploying consolidate?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/betofrega-consolidate

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Consolidate canonical product knowledge, ideas, behavior, decisions, increments, and evidence; route technical decisions and reconcile delivery, exposure, and flags.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/consolidate

What's inside

Skill name
consolidate
Description
Consolidate canonical product knowledge, ideas, behavior, decisions, increments, and evidence; route technical decisions and reconcile delivery, exposure, and flags.
License
MIT
Instructions
73 lines in SKILL.md · view on GitHub

Files (18)

  • LICENSE
  • SKILL.md
  • openai.yaml · agents/
  • delivery-slice-template.md · assets/
  • functionality-template.md · assets/
  • technical-spec-template.md · assets/
  • artifact-links.md · references/
  • catalogue.md · references/
  • context.md · references/
  • decisions.md · references/
  • delivery-slice-example.md · references/
  • delivery-slices.md · references/
  • functionality-example.md · references/
  • local-document-delivery.md · references/
  • proposals.md · references/
  • reconciliation.md · references/
  • record-format.md · references/
  • technical-work.md · references/

SKILL.md (first lines)

# Consolidate

Maintain product intent, behavior, authority, and evidence for owners and agents
across sessions. Adapt representation, hierarchy, workflow, and depth to the product;
cover its relevant contract. Apply [artifact links](references/artifact-links.md)
whenever citing documents or tickets.

## Resolve authority and intent

Resolve [project configuration](../setup-beto-frega-skills/references/project-configuration.md#resolve-configuration),
including external files. Read canonical destinations, native representation,
conventions, governing decisions, maintenance sources, affected records, and existing
authorization. Preserve identifiers and settled choices.

Setup owns configuration. For an unresolved destination or convention, name the gap
and suggest `$setup-beto-frega-skills`. Continue the work you have authority for, and
write clearly labeled drafts where a write is blocked. Canonical records keep
precedence over drafts, and an unavailable configured destination stays a named gap.

Read only relevant routes; combine them when needed:

| Route | Read when |
| --- | --- |
| [Catalogue](references/catalogue.md) | Finding or maintaining functionalities, audiences, jobs, behavior, value, and cost. |
| [Delivery slices](references/delivery-slices.md) | Recording selected increments, acceptance, dependencies, exposure, coverage, or delivery evidence. |
| [Context](references/context.md) | Maintaining direction, business context, shared rules, vocabulary links, or discovery evidence. |
| [Decisions](references/decisions.md) | Recording product/business choices, rationale, history, or their contract consequences. |
| [Proposals](references/proposals.md) | Shaping an investment proposal or pitch. |
| [Technical work](references/technical-work.md) | Preserving technical choices or preparing a scoped tracker spec. |
| [Reconciliation](references/reconciliation.md) | Maintaining implementation, deployment, release, exposure, or flags; investigating drift. |

Use [write-adr](../write-adr/SKILL.md) for architecture and the
[glossary format](../domain-modeling/CONTEXT-FORMAT.md) for definitions under configured
domain conventions. Feature behavior belongs in the catalogue; cross-functional
rules have shared authority. Link derived specs and tickets to those records.

Consolidate known knowledge; grill only consequential gaps blocking this update.
Interview handoffs retain selected increments, confirmed product/technical choices,
references, and deferred questions. Feature knowledge and ideas may exceed selected
delivery scope.

## Write the affected knowledge

Read [record format](references/record-format.md) before writing living records;
it owns consolidation, native history, bounded changelogs, template, and example.

Keep approval, proposals, observations, and assumptions apart. Approval comes from
the conversation or project evidence; code and flag configuration alone do not show it. Preserve
unknowns and discrepancies; actual-state claims carry source, time, scope, and coverage.

Use configured objects, properties, sections, and relationships. Keep one authority
per meaning; cover known behavior, exceptions, and implementation/verification
scenarios. Scale detail and governance to the product, but cover every rule. Update
linked records affected by accepted changes. Label interaction illustrations
replaceable and state binding outcomes explicitly.

Act within existing authorization. Release, flag operations, schedules, and new
policy need their own authorization. Read reconciliation
before an authorized flag operation.

## Verify completion

Apply [local document delivery](references/local-document-delivery.md) for local edits.
Read back saved records and relationships: verify identity, representation, content,
authority/timing, source coverage, decision/shared-rule/work/evidence links, and the
whole-document record-format checks. Account for every affected record with a
verified result or named gap.

For lookups/reviews, return canonical links and findings. For changes, report saved,
proposed, unknown, and unverifiable effects separately. Report drafts, acceptance,
implementation, and verified release as separate outcomes.

From BetoFrega/skills, MIT.

More from BetoFrega/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 21, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from BetoFrega

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get consolidate running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying consolidate?

CallGet help
Cite this page

consolidate skill. Agent Mart. https://agentmart.dev/skills/betofrega-consolidate (last updated 2026-10-24)