Agent skill

Conditional Customer Success

by magnus919 in magnus919/agent-skills

Guide recurring human-relationship practices — success plans, health evidence, renewal and expansion signals, QBRs, handoffs, escalation, and closed-loop Voice of Customer.

MITAuto-check passedSales & Support

Install Conditional Customer Success

skills CLI
$ npx skills add magnus919/agent-skills --skill conditional-customer-success -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install magnus919/agent-skills conditional-customer-success --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/magnus919/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/conditional-customer-success .claude/skills/conditional-customer-success && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
conditional-customer-success
GitHub stars
115
Token cost
~4.1k tokens
SKILL.md length
1,748 words
Files
9 (incl. references)
Skills in repo
131
Repo updated
First seen
Licence
MIT

At a glance

Guide recurring human-relationship practices — success plans, health evidence, renewal and expansion signals, QBRs, handoffs, escalation, and closed-loop Voice of Customer.

  • Works in 10 steps: B2B Subscription → Transactional (Non-Subscription) → Public Service → …
  • Products without accounts
  • SKILL.md covers When to Load (Should-Trigger…, When not to use, When NOT to Load… and Product/Relationship Models, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Conditional Customer Success is an agent skill from magnus919/agent-skills. Guide recurring human-relationship practices — success plans, health evidence, renewal and expansion signals, QBRs, handoffs, escalation, and closed-loop Voice of Customer. Do not use this skill for products without accounts, renewals, QBRs, or a customer-success team, including some internal tools, pure transactional products without recurring relationships, and public services without account-based engagement. Load only when the product context includes a recurring human relationship; decline or route away…

Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `README.md`, `evals/evals.json` and `references/discovery-brief.md`).

It sits in Sales & Support, covering Customer success. The repository describes itself as: Curated collection of AI agent skills for Hermes and other agent frameworks. The licence is MIT.

When your agent uses it

  • Products without accounts
  • A customer-success team
  • Including some internal tools
  • Pure transactional products without recurring relationships

Example prompts

  • “/conditional-customer-success”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. B2B Subscription
  2. Transactional (Non-Subscription)
  3. Public Service
  4. Internal Product
  5. Applicability Decision
  6. Success Plan
  7. Health / Risk Record
  8. Escalation Path
  9. Handoff Protocols
  10. Closed-Loop Feedback Closure

What it can do on your machine

Read from SKILL.md and the folder at commit 22b4723. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Conditional Customer Success loads about 4.1k tokens when it runs, and up to ~7.7k if it reads all its reference files. Until then it costs about 138 tokens; SKILL.md has 1,748 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~138
When it runs · the whole SKILL.md, loaded when a task matches
~4.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from magnus919/agent-skills at commit 22b4723, republished under its MIT licence (© magnus919). 1,748 words, ~4,111 tokens.

Download SKILL.mdSave it as .claude/skills/conditional-customer-success/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
conditional-customer-success
description
Guide recurring human-relationship practices — success plans, health evidence, renewal and expansion signals, QBRs, handoffs, escalation, and closed-loop Voice of Customer. Do not use this skill for products without accounts, renewals, QBRs, or a customer-success team, including some internal tools, pure transactional products without recurring relationships, and public services without account-based engagement. Load only when the product context includes a recurring human relationship; decline or route away otherwise.
license
MIT
metadata.tags
customer-success, success-plan, health-evidence, renewal, expansion, QBR, escalation, handoff, voice-of-customer, feedback-closure, account-management, B2B…

Conditional Customer Success

A CONDITIONAL skill for products with recurring human relationships. This skill must never be loaded for every product context. It loads only when the product has accounts, renewals, QBRs, or a dedicated customer-success team. When those conditions are absent — for internal tools, pure transactional products, or public services without account-based engagement — this skill declines and routes the caller away.

When to Load (Should-Trigger Examples)

ExampleWhat makes it a match
B2B subscription product with named account managersAccounts, renewals, dedicated CS team
Enterprise SaaS with quarterly business reviewsQBR cadence, account-tier engagement
Renewal-risk analysis needed for a contract portfolioRenewal evidence, churn-risk signals
Product with an assigned customer-success team managing health plansSuccess plans, health tracking
Account-expansion opportunity identified but adoption signals are mixedExpansion with relationship context
Customer feedback loop — insight surfaced, product change made, customer communication neededClosed-loop Voice of Customer

When not to use

This skill must not be loaded for products without accounts, renewals, QBRs, or a customer-success team. See the should-not-trigger examples below.

When NOT to Load (Should-Not-Trigger Examples)

This skill must not load when the product context lacks the required preconditions. The skill must decline and route the caller away.

ExampleWhy it does not apply
Internal developer tool with no accounts, no renewals, no QBRsNo recurring human relationship; no CS team
Pure transactional e-commerce product — one-time purchases, no account managementNo accounts, no renewals, no QBRs, no CS team
Public-service benefit-application portal — no account-tier engagement, no CS teamNo accounts (in the CS sense), no renewals, no QBRs
Consumer mobile game with subscription billing but no human CS relationshipSubscription alone is insufficient; no human CS relationship
Open-source project with community support but no paid accountsNo accounts, no renewals, no CS team
Internal analytics dashboard for a single teamNo recurring relationship outside the team; no CS team

Decline rule: If none of the should-trigger conditions are present — that is, the product has no accounts, no renewals, no QBRs, and no customer-success team — this skill must decline with an applicability assessment that records which preconditions were absent and routes the caller to the nearest appropriate skill (product-analytics-and-measurement, product-adoption, or product-lifecycle-learning).

Product/Relationship Models

This skill defines when customer-success practice applies and what adaptations are needed for four distinct models. None assumes SaaS.

1. B2B Subscription

Applies fully. Accounts, renewals, QBRs, expansion tiers, and a dedicated customer-success team are the canonical fit. All artifacts apply: success plans, health/risk records, escalation paths, handoff protocols, and closed-loop feedback.

2. Transactional (Non-Subscription)

Partial application — adapted. The product may have repeat customers and account relationships without formal subscriptions. CS adaptations:

  • Success plans focus on repeat-purchase patterns and re-order outcomes, not subscription renewal dates.
  • Health evidence uses purchase frequency, order-value trends, and account engagement signals — not MRR or churn metrics.
  • QBRs become periodic business reviews triggered by purchase milestones or account tier, not calendar dates.
  • Escalation triggers on declining purchase frequency or account dormancy.
3. Public Service

Minimal application — routing preferred. Public-service products often have citizens or beneficiaries, not "accounts." CS applies only when there is explicit account-based engagement (e.g., a case-management portal).

  • Success plans become service-outcome plans, not commercial plans.
  • Health evidence uses service-access equity, completion-rate gaps across cohorts, and accessibility barriers — never commercial metrics.
  • Escalation routes to program governance, not commercial leadership.
  • Privacy boundaries are stricter: citizen data must not be repurposed. See references/privacy-and-human-judgment.md.

When no account-based engagement exists, decline and route to product-adoption (for service-adoption diagnostics) and product-analytics-and-measurement (for service-outcome measurement).

4. Internal Product

Conditional — strong routing preference. Internal products may have "internal customers" (other teams, business units), but CS applies only when there is a recurring human relationship with structured engagement.

  • Success plans become internal service-level agreements, not commercial plans.
  • Health evidence uses internal adoption, workflow-completion, and time-saved metrics — never revenue or MRR.
  • QBRs become internal service reviews, structured around team outcomes.
  • Escalation routes to internal governance, not commercial leadership.

When the internal product has no recurring human relationship (e.g., a single-team analytics dashboard), decline and route to product-adoption or product-lifecycle-learning.

Core Artifacts

Every artifact is a decision-support tool, never an automated decision.

1. Applicability Decision

Before applying any customer-success method, produce an applicability assessment. If the product context lacks accounts, renewals, QBRs, or a CS team, decline and route the caller away. Record which preconditions were absent.

Template: templates/applicability-decision.md

2. Success Plan

A structured record of the customer's desired outcomes, aligned product capabilities, measurable milestones, and assigned relationship owner. Not a sales plan; not a support ticket; not a project plan. The success plan is the living artifact that connects customer intent to product evidence.

Template: templates/success-plan.md

3. Health / Risk Record

An evidence-based record — never an automated score. For each health dimension, capture:

  • The signal (observable evidence, not a proxy metric).
  • The source (analytics, adoption, direct observation).
  • The trend (direction and recency).
  • The confidence (how reliable the evidence is).
  • Conflicting signals (surface disagreement, not a forced consensus).

Template: templates/health-risk-record.md

4. Escalation Path

A defined path from signal to decision-maker, with explicit human-judgment gates. Every escalation requires a human decision before action. The path defines:

  • The trigger signal and its threshold.
  • The escalation owner (named role, not a system).
  • The review cadence.
  • The decision options (and who makes each).
  • The fallback if no decision is reached.

Template: templates/escalation-and-feedback-closure.md

5. Handoff Protocols

Defined handoffs to product, support, and engineering teams with clear ownership boundaries:

HandoffTriggerReceiving TeamArtifact
Feature request from customer evidenceValidated pattern across ≥3 accountsProductSuccess-plan extract + health evidence
Support escalationBlocking issue with account impactSupportEscalation record with account context
Technical defect with account riskReproducible bug affecting ≥1 accountEngineeringDefect record + account-impact assessment
Churn risk requiring lifecycle actionSustained health decline, 2+ remediation attempts failedProduct-lifecycle-learningHealth/risk record + remediation history
6. Closed-Loop Feedback Closure

The path from customer insight to product change to customer communication:

Customer Insight → Validate (pattern? isolated?) →
  Product Decision (build / defer / decline) →
    Implementation → Communication Back to Customer →
      Close Loop (record evidence)

Every step is recorded. "Communication Back to Customer" is mandatory — closing the loop means the customer knows what happened with their feedback. See templates/escalation-and-feedback-closure.md.

Privacy and Human Judgment Boundaries

These boundaries are non-negotiable.

Customer Feedback Must Not Become Surveillance
  • Feedback is collected with consent and a stated purpose.
  • Usage is limited to the stated purpose.
  • Aggregation is permitted for pattern detection; individual-level behavior tracking beyond the stated purpose is not.
  • Customer data shared across teams is scoped to the minimum necessary.
Show full SKILL.md (695 more words)Show less
Health Scores Are Decision-Support, Not Automated Decisions
  • A health signal is evidence; it never becomes an automated action (no auto-churn, no auto-escalation without human review).
  • Conflicting signals must be surfaced, not averaged into a single score.
  • The health/risk record includes confidence and provenance for every signal.
Human Judgment Is Required for Escalation Decisions
  • Every escalation trigger requires a human decision before any action.
  • The escalation path defines who decides, on what evidence, with what options.
  • A "no decision" state has a defined fallback — escalate further, not auto-act.
Privacy Boundaries Around Customer Data
  • Customer-identifiable data is never embedded in templates shared outside the CS team.
  • Health evidence uses anonymized or aggregated signals when shared across teams.
  • Data retention and access are governed by the product's privacy policy, not the CS practice.

See references/privacy-and-human-judgment.md for the full boundaries reference.

This skill routes to specialist skills rather than re-deriving their methodology. All routing references use relative paths to existing directories, or prose references for skills not yet landed.

Routes to (existing skills)
SkillWhat it ownsHow this skill consumes it
../product-analytics-and-measurement/SKILL.mdMetric trees, tracking plans, instrumentation QA, measurement governanceProvides health evidence and metric definitions for health/risk records
../product-adoption/SKILL.mdOnboarding, activation, behavior change, feature discovery, sustained useProvides adoption signals (activation, feature adoption, sustained use) as health dimensions
../product-experimentation/SKILL.mdExperiment design, readout, ship/no-ship decisionsConsumed when CS evidence suggests an experiment (e.g., intervention test for at-risk accounts)
../go-to-market/SKILL.mdAcquisition campaigns, marketing conversionDoes NOT own. CS consumes acquisition context only.
../crm/SKILL.mdHubSpot CRM operations — contact records, deal pipeline views, confirmed deal stage changesProvides account records and pipeline/health context for health/risk records and QBR preparation
Routes to (prose references — skills not yet landed)
SkillWhat it ownsHow this skill routes to it
product-lifecycle-learningRetirement communication plans, customer treatment during sunset, migration-support coordination, churn-pattern learning across the portfolioEscalates sustained health decline (2+ remediation attempts failed) for lifecycle action. Routes churn and sunset signals for portfolio-level learning.
Does NOT own
  • Statistical inference or experiment design — belongs to data-scientist and product-experimentation.
  • Product-analytics instrumentation — belongs to product-analytics-and-measurement.
  • Acquisition, marketing conversion, or campaign design — belongs to go-to-market.
  • Product roadmapping or portfolio prioritization — belongs to product-roadmapping-and-portfolio.
  • Customer support operations or ticket management — belongs to support-tooling skills.
  • Contract negotiation, pricing, or legal terms — belongs to go-to-market and legal-strategy skills.

File Map

FilePurposeLoad when
references/discovery-brief.mdMaps existing related content, ownership boundaries, and routing decisionsFirst load — required context
references/privacy-and-human-judgment.mdFull privacy and human-judgment boundaries, surveillance-risk guidance, consent frameworkPrivacy or judgment question arises
templates/applicability-decision.mdStructured applicability assessment — decline or proceed with evidenceCustomer-success method considered for any product
templates/success-plan.mdCustomer success plan with desired outcomes, milestones, evidence gatesBuilding or reviewing a success plan
templates/health-risk-record.mdEvidence-based health/risk record with signal, source, trend, confidence, and conflicting-signal trackingHealth review, QBR prep, renewal-risk analysis
templates/escalation-and-feedback-closure.mdEscalation path definition and closed-loop feedback closure recordEscalation design or feedback-loop operation

QBR and Engagement Cadence

Quarterly Business Review (QBR) Structure

A QBR is an evidence review, not a sales presentation. The structure:

  1. Success-plan review — progress against desired outcomes, milestone achievement.
  2. Health evidence — each dimension, its signal, trend, and confidence. Conflicting signals presented, not averaged.
  3. Adoption evidence — feature adoption, activation trends, sustained-use patterns (from product-adoption evidence).
  4. Risk review — open risks, mitigation status, escalation history.
  5. Forward plan — next-period success-plan adjustments, expansion opportunities (routed to go-to-market for commercial motion), and risk-mitigation actions.
  6. Feedback loop status — open feedback items, product decisions made, communication-back status.
Triggering QBRs Outside B2B Subscription

For non-subscription models, QBRs are triggered by events, not calendar dates:

ModelQBR Trigger
TransactionalPurchase-milestone threshold, account-tier change, or 6-month dormancy
Public ServiceService-review cycle, equity-gap detection, or accessibility-audit result
Internal ProductInternal service-review cycle, team-reorg, or adoption decline

Output Contract

  1. An applicability decision recorded before any CS method is applied.
  2. A success plan with desired outcomes, milestones, evidence gates, and a named relationship owner.
  3. A health/risk record with evidence per dimension, not a score.
  4. An escalation path with explicit human-judgment gates.
  5. A closed-loop record tracing customer insight → product decision → customer communication.
  6. Handoff records to product, support, or engineering with account context and evidence.

© magnus919, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in conditional-customer-success of magnus919/agent-skills.

  • SKILL.md
  • README.md
  • evals/evals.json
  • references/discovery-brief.md
  • references/privacy-and-human-judgment.md
  • templates/applicability-decision.md
  • templates/escalation-and-feedback-closure.md
  • templates/health-risk-record.md
  • templates/success-plan.md

Open the folder on GitHubat commit 22b4723

Compare with similar skills

Conditional Customer Success next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Conditional Customer Success compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Conditional Customer Success this skillmagnus919/agent-skills115—~4.1kAutomated safety check: PassMIT
Cs Health Scorecardmohitagw15856/pm-claude-skills1.4k—~2.4kAutomated safety check: PassMIT
Youtube SearchZeroPointRepo/youtube-skills1k1 repos~1.8kAutomated safety check: PassMIT
YtZeroPointRepo/youtube-skills1k1 repos~951Automated safety check: PassMIT
Account PlanBevel-Software/Hexis100—~2.1kAutomated safety check: PassApache-2.0
Loki Modedavila7/claude-code-templates33k7 repos~7.1kAutomated safety check: WarnMIT

Similar skills

  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated 2 days ago
    Sales & SupportAuto-check passed
  • Youtube Search

    ZeroPointRepo/youtube-skills

    A skill your agent uses when the user wants to find YouTube content on any topic: searching for videos or channels, finding creators who cover a subject, discovering tutorials, talks, or expert…

    1k GitHub starsUsed in 1 repo~1.8k tokens
    Sales & SupportAuto-check passed
  • Yt

    ZeroPointRepo/youtube-skills

    A skill your agent uses when YouTube is relevant: pasted video links or IDs, @handles, quick video lookups, summaries, channel latest uploads, topic search, or any request involving YouTube content…

    1k GitHub starsUsed in 1 repo~951 tokens
    Sales & SupportAuto-check passed
  • Account Plan

    Bevel-Software/Hexis

    Build or refresh a strategic account plan - current state, goals, stakeholder coverage, opportunity map, risks, and the action plan - written to a doc and key fields synced to the CRM.

    100 GitHub stars~2.1k tokensUpdated today
    Sales & SupportAuto-check passed
  • Loki Mode

    davila7/claude-code-templates

    Multi-agent autonomous startup system for Claude Code. An agent skill from davila7/claude-code-templates.

    33k GitHub starsUsed in 7 repos~7.1k tokens
    Sales & SupportAuto-check: warnings
  • Account Research

    explorium-ai/gtm-skills

    Account research skill for Claude Code and Codex: generate a high-signal company intelligence brief including firmographics, technographics, funding history, hiring signals, business events, recent…

    185 GitHub stars~2.8k tokensUpdated 3 days ago
    Sales & SupportAuto-check passed

More from magnus919/agent-skills

All 131 skills in this repo
  • Artifact Pyramids

    magnus919/agent-skills

    Organize durable agent research outputs as summaries, analysis, and evidence dossiers.

    119 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Ascii City Engine

    magnus919/agent-skills

    Build portable, first-person colored ASCII city engines and small GIS-derived city packs.

    119 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Color Management

    magnus919/agent-skills

    Manage color workflows with ICC profiles, working spaces, gamut mapping, and color science.

    119 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Data Scientist

    magnus919/agent-skills

    A skill your agent uses for PhD-level expertise in data science, statistics, and machine learning: rigorous statistical analysis, experimental design, causal inference, advanced modeling, research…

    119 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • Docker Compose

    magnus919/agent-skills

    Use Docker Compose to define, run, debug, and harden multi-container applications.

    119 GitHub stars~2k tokensUpdated today
    Auto-check: notes
  • Fpga Development

    magnus919/agent-skills

    Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence.

    119 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Categories

Questions about Conditional Customer Success

What does Conditional Customer Success do?

Guide recurring human-relationship practices — success plans, health evidence, renewal and expansion signals, QBRs, handoffs, escalation, and closed-loop Voice of Customer. Conditional Customer Success is an agent skill from magnus919/agent-skills. Guide recurring human-relationship practices — success plans, health evidence, renewal and expansion signals, QBRs, handoffs, escalation, and closed-loop Voice of Customer.

When should I use Conditional Customer Success?

Conditional Customer Success fits situations like: products without accounts; A customer-success team; including some internal tools; pure transactional products without recurring relationships.

How do I install Conditional Customer Success in Claude Code?

Run `npx skills add magnus919/agent-skills --skill conditional-customer-success -a claude-code`. Or copy the skill folder (conditional-customer-success in magnus919/agent-skills) into .claude/skills/conditional-customer-success in your project. Claude Code loads it when a task matches its description.

How do I install Conditional Customer Success in Codex?

Run `npx skills add magnus919/agent-skills --skill conditional-customer-success -a codex`. Or copy the skill folder (conditional-customer-success in magnus919/agent-skills) into .agents/skills/conditional-customer-success in your project. Codex loads it when a task matches its description.

Can I use Conditional Customer Success in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add magnus919/agent-skills --skill conditional-customer-success -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/conditional-customer-success, .gemini/skills/conditional-customer-success, .github/skills/conditional-customer-success and .opencode/skills/conditional-customer-success in your project.

What does Conditional Customer Success need to run?

SKILL.md names no scripts, command-line tools or credentials: Conditional Customer Success is instructions for the agent only.

Does Conditional Customer Success access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Conditional Customer Success safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Conditional Customer Success use?

Conditional Customer Success is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Conditional Customer Success use?

About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.6k tokens, read only when the agent opens those files.

What are the alternatives to Conditional Customer Success?

Skills that share tags, products or a category with Conditional Customer Success: Cs Health Scorecard (mohitagw15856/pm-claude-skills, 1.4k stars), Youtube Search (ZeroPointRepo/youtube-skills, 1k stars), Yt (ZeroPointRepo/youtube-skills, 1k stars) and Account Plan (Bevel-Software/Hexis, 100 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Conditional Customer Success?

magnus919 (a GitHub user) maintains it in magnus919/agent-skills, which has 115 GitHub stars. The repository holds 131 skills in this directory. The repository was last updated on October 10, 2026.

Source: magnus919/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.