Updated 5d ago
by Sahil-SS9
agent-personas
Portable skills, personas and bundles for dedicated agents across multiple harnesses
54 GitHub stars (54)
| Period | New stars |
|---|---|
| Oct 15 | +4 |
| Oct 16 | 0 |
- 30 skills (30 skills found in its SKILL.md files)
- 4 forks (4 forks)
- 5d ago last update (Last updated 5d ago)
Install
Skills CLI
npx skills add Sahil-SS9/agent-personas
Asks which skills and agents to install. Just one: npx skills add Sahil-SS9/agent-personas --skill accessible-dynamic-components — add -g for every project.
Claude Code
git clone https://github.com/Sahil-SS9/agent-personascp -r "agent-personas/skills/accessible-dynamic-components" ~/.claude/skills/
Copies the accessible-dynamic-components skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Sahil-SS9/agent-personas
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 308 files.
-
accessible-dynamic-components
Make dynamic and JS-driven UI accessible: focus, live regions, and state.
skills/accessible-dynamic-components/SKILL.md on GitHub (opens in a new tab) -
agent-artifact-attribution-and-scratch-routing
Attribute debris to the agent session that created it — with evidence — and route future agent scratch output to a home that will not accumulate.
skills/agent-artifact-attribution-and-scratch-routing/SKILL.md on GitHub (opens in a new tab) -
agent-change-governance
Record agent changes, approvals, handoffs and verified outcomes.
skills/agent-change-governance/SKILL.md on GitHub (opens in a new tab) -
agent-config-validation
Validate agent configuration against its actual runtime schema.
skills/agent-config-validation/SKILL.md on GitHub (opens in a new tab) -
agent-dispatch-discipline
Brief, dispatch and verify agent work so nothing depends on session memory.
skills/agent-dispatch-discipline/SKILL.md on GitHub (opens in a new tab) -
agent-loop-guardrails
Wrap agent loops in deterministic gates, scoped permissions and stop rules.
skills/agent-loop-guardrails/SKILL.md on GitHub (opens in a new tab) -
agent-profile-review
Weekly independent review of all specialist profiles by.
skills/agent-profile-review/SKILL.md on GitHub (opens in a new tab) -
ai-task-suitability-review
Choose bounded AI roles without expanding authority.
skills/ai-task-suitability-review/SKILL.md on GitHub (opens in a new tab) -
analysis-capability-ladder
Pick the strongest analysis level available, discover and propose new tools when a gap blocks the answer, state the level used, and finish within budget.
skills/analysis-capability-ladder/SKILL.md on GitHub (opens in a new tab) -
analytics-dimensional-modelling
Model analytics data dimensionally: facts, dimensions, grain and slowly-changing history.
skills/analytics-dimensional-modelling/SKILL.md on GitHub (opens in a new tab) -
angr-symbolic-adapter
Use angr for symbolic analysis when evidence needs justify it: constraint solving on parsers, decoders and guarded paths, with coverage honesty.
skills/angr-symbolic-adapter/SKILL.md on GitHub (opens in a new tab) -
api-compatibility-analysis
Classify every proposed API change as compatible or breaking across all three dimensions.
skills/api-compatibility-analysis/SKILL.md on GitHub (opens in a new tab) -
api-security-design
Design API security: authentication, authorization, rate limiting and abuse controls.
skills/api-security-design/SKILL.md on GitHub (opens in a new tab) -
architecture-characteristics-driven-design
Elicit the few driving quality attributes and give each a measurable target.
skills/architecture-characteristics-driven-design/SKILL.md on GitHub (opens in a new tab) -
architecture-decision-records
Capture each irreversible decision as a superseding ADR.
skills/architecture-decision-records/SKILL.md on GitHub (opens in a new tab) -
architecture-deepening-review
Find architectural deepening opportunities in a.
skills/architecture-deepening-review/SKILL.md on GitHub (opens in a new tab) -
architecture-documentation
Produce C4-level diagrams and ADR records that survive review.
skills/architecture-documentation/SKILL.md on GitHub (opens in a new tab) -
architecture-layering-review
Verify layered-architecture boundaries before commit.
skills/architecture-layering-review/SKILL.md on GitHub (opens in a new tab) -
aria-semantic-authoring
Build accessible UI from semantic HTML first, ARIA only where needed.
skills/aria-semantic-authoring/SKILL.md on GitHub (opens in a new tab) -
artefact-triage-preservation
Triage unknown files safely: identify, fingerprint, chain-of-custody and preserve evidence before any analysis.
skills/artefact-triage-preservation/SKILL.md on GitHub (opens in a new tab) -
arxiv
Search arXiv papers by keyword, author, category, or ID.
skills/arxiv/SKILL.md on GitHub (opens in a new tab) -
asset-and-bundle-budgets
Enforce asset, bundle and delivery budgets; ship less by default.
skills/asset-and-bundle-budgets/SKILL.md on GitHub (opens in a new tab) -
attack-path-modelling
Model plausible attack paths across the kill chain and map coverage gaps.
skills/attack-path-modelling/SKILL.md on GitHub (opens in a new tab) -
attck-control-mapping
Map every plausible attack tactic to a detection and a response; gaps are the work plan.
skills/attck-control-mapping/SKILL.md on GitHub (opens in a new tab) -
audit-engine
Systematic audit of workflows, services, skills, and.
skills/audit-engine/SKILL.md on GitHub (opens in a new tab) -
automated-a11y-ci
Wire automated accessibility checks into CI to catch regressions early.
skills/automated-a11y-ci/SKILL.md on GitHub (opens in a new tab) -
automation-cost-budgeting
Keep automations within cost and rate-limit budgets so they don't run away.
skills/automation-cost-budgeting/SKILL.md on GitHub (opens in a new tab) -
automation-secrets-handling
Handle credentials in automations safely: no plaintext, least privilege, rotation.
skills/automation-secrets-handling/SKILL.md on GitHub (opens in a new tab) -
backend-api-latency
Reduce API and backend latency: queries, N+1, payloads and caching.
skills/backend-api-latency/SKILL.md on GitHub (opens in a new tab) -
backend-contract-design
Design backend-neutral contracts that real backends satisfy.
skills/backend-contract-design/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
skillsby anthropics Public repository for Agent Skills