mcpbeat Sign in

Absolute Upgrade Agent Skill

> Triggers on "absolute upgrade", "upgrade our dependencies", "bump deps", "update packages", "move off the deprecated X", "clear the Dependabot backlog".

3k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
0
copies elsewhere
how many repositories repackaged it
205
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/maddhruv/absolute --skill absolute-upgrade

The instruction itself

7 sections, as written by the author

> Start your first response with the ⬆️ emoji.

Absolute Upgrade

Bring dependencies current — safely, in risk-ranked waves, with tests green after each.

Not a blind npm update: outdated and vulnerable deps are grouped by blast radius

(patch/minor → safe wave; major/breaking → gated, one at a time, changelog-read), applied

incrementally, and verified against the project's own test suite.

Runs the shared engine in references/health-engine.md — read it for the

DETECT → SCAN → TRIAGE → FIX → VERIFY → REPORT loop and the safety contract. This file

covers only what's specific to dependency upgrades.


When to use

  • Routine "bring deps up to date" / "upgrade our dependencies".
  • A specific bump: "upgrade React to 19", "move off the deprecated X package".
  • Clearing npm outdated / Dependabot backlog without 40 separate PRs.

Not for: adding a *new* dependency (that's a work/feature decision), or auditing

*vulnerabilities* specifically → use /absolute audit (it triages CVEs; upgrade

moves versions).


What it scans

Per ecosystem, list outdated deps with current → wanted → latest and the jump type:

| Ecosystem | Detect outdated | Lockfile / manifest |

|---|---|---|

| npm | npm outdated --json | package-lock.json |

| pnpm | pnpm outdated --format json | pnpm-lock.yaml |

| yarn | yarn outdated --json | yarn.lock |

| Python (pip) | pip list --outdated --format=json | requirements*.txt |

| Python (poetry/uv) | poetry show --outdated / uv pip list --outdated | pyproject.toml + lock |

| Go | go list -u -m -json all | go.mod / go.sum |

Also flag: deps with known deprecations, duplicate/multiple versions of the same package,

and direct vs transitive (only direct deps are upgrade targets; transitives follow).


Risk ranking (TRIAGE)

Group the upgrade plan into waves by semver jump — safest first:

| Wave | Jump | Default |

|---|---|---|

| 1 | patch (x.y.Z) | batch together, fix now |

| 2 | minor (x.Y.z) | batch by package family, fix now |

| 3 | major (X.y.z) / pre-1.0 minor | one at a time, gated — read the changelog/migration guide first, list breaking changes |

For every major bump: locate breaking changes (CHANGELOG, release notes, codemod if the

package ships one), inventory call sites that touch the changed API, and state the

migration before applying. Peer-dependency conflicts get resolved in the same wave as

their driver.


Fix & verify

  • Apply a wave, regenerate the lockfile, run the project's full test + build (a passing

install is not a passing upgrade).

  • Majors: apply the version bump *and* the required code migration in the same wave, or the

build breaks. Use the package's codemod where one exists.

  • A wave that can't go green within reason → revert it, report it as blocked with the error,

keep the green waves. Never --force / --legacy-peer-deps to mask a real conflict.


Gotchas

  • Lockfile-only "upgrade". Bumping the manifest without regenerating + committing the

lockfile ships untested transitive versions. Always regenerate.

  • Batching a major in with patches. One breaking bump fails the whole wave and hides

which change broke it. Majors are always solo.

  • Green install ≠ green project. npm install succeeding proves nothing — run tests.
  • Pinning around a failure. If a bump breaks something, fix or defer it; don't pin the

dependency tree to dodge it silently.


Companion commands

  • /absolute audit — if the goal is fixing *vulnerabilities*, start there; it'll route

back here for the version moves.

  • /absolute deflake — flaky tests can mask whether an upgrade truly passed.
  • /absolute work — if an upgrade needs real feature-level migration work, hand off.

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take maddhruv/absolute-upgrade from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference uv, npm. Without those the skill loads but fails at the first command.